diff --git "a/HalfCheetah-v4/Train_single_HalfCheetah-v4_PPO_20230526-133418/logs/log.txt" "b/HalfCheetah-v4/Train_single_HalfCheetah-v4_PPO_20230526-133418/logs/log.txt" new file mode 100644--- /dev/null +++ "b/HalfCheetah-v4/Train_single_HalfCheetah-v4_PPO_20230526-133418/logs/log.txt" @@ -0,0 +1,2085 @@ +2023-05-26 13:34:18 - SimpleLog - INFO: - General Configs: +2023-05-26 13:34:18 - SimpleLog - INFO: - ================================================================================ +2023-05-26 13:34:18 - SimpleLog - INFO: - Name Value Type +2023-05-26 13:34:18 - SimpleLog - INFO: - env_name gym +2023-05-26 13:34:18 - SimpleLog - INFO: - algo_name PPO +2023-05-26 13:34:18 - SimpleLog - INFO: - mode train +2023-05-26 13:34:18 - SimpleLog - INFO: - device cuda +2023-05-26 13:34:18 - SimpleLog - INFO: - seed 1 +2023-05-26 13:34:18 - SimpleLog - INFO: - max_episode 2000 +2023-05-26 13:34:18 - SimpleLog - INFO: - max_step 1000 +2023-05-26 13:34:18 - SimpleLog - INFO: - collect_traj 0 +2023-05-26 13:34:18 - SimpleLog - INFO: - mp_backend single +2023-05-26 13:34:18 - SimpleLog - INFO: - n_workers 2 +2023-05-26 13:34:18 - SimpleLog - INFO: - n_learners 1 +2023-05-26 13:34:18 - SimpleLog - INFO: - share_buffer 1 +2023-05-26 13:34:18 - SimpleLog - INFO: - online_eval 1 +2023-05-26 13:34:18 - SimpleLog - INFO: - online_eval_episode 10 +2023-05-26 13:34:18 - SimpleLog - INFO: - model_save_fre 500 +2023-05-26 13:34:18 - SimpleLog - INFO: - load_checkpoint 0 +2023-05-26 13:34:18 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_DQN_20230515-211721 +2023-05-26 13:34:18 - SimpleLog - INFO: - load_model_step best +2023-05-26 13:34:18 - SimpleLog - INFO: - ================================================================================ +2023-05-26 13:34:18 - SimpleLog - INFO: - Algo Configs: +2023-05-26 13:34:18 - SimpleLog - INFO: - ================================================================================ +2023-05-26 13:34:18 - SimpleLog - INFO: - Name Value Type +2023-05-26 13:34:18 - SimpleLog - INFO: - independ_actor 1 +2023-05-26 13:34:18 - SimpleLog - INFO: - share_optimizer 0 +2023-05-26 13:34:18 - SimpleLog - INFO: - ppo_type clip +2023-05-26 13:34:18 - SimpleLog - INFO: - eps_clip 0.2 +2023-05-26 13:34:18 - SimpleLog - INFO: - kl_target 0.1 +2023-05-26 13:34:18 - SimpleLog - INFO: - kl_lambda 0.5 +2023-05-26 13:34:18 - SimpleLog - INFO: - kl_beta 1.5 +2023-05-26 13:34:18 - SimpleLog - INFO: - kl_alpha 2 +2023-05-26 13:34:18 - SimpleLog - INFO: - continuous 1 +2023-05-26 13:34:18 - SimpleLog - INFO: - gamma 0.95 +2023-05-26 13:34:18 - SimpleLog - INFO: - k_epochs 8 +2023-05-26 13:34:18 - SimpleLog - INFO: - lr 0.0001 +2023-05-26 13:34:18 - SimpleLog - INFO: - actor_lr 0.0003 +2023-05-26 13:34:18 - SimpleLog - INFO: - critic_lr 0.001 +2023-05-26 13:34:18 - SimpleLog - INFO: - critic_loss_coef 0.5 +2023-05-26 13:34:18 - SimpleLog - INFO: - entropy_coef 0.01 +2023-05-26 13:34:18 - SimpleLog - INFO: - batch_size 256 +2023-05-26 13:34:18 - SimpleLog - INFO: - sgd_batch_size 128 +2023-05-26 13:34:18 - SimpleLog - INFO: - actor_hidden_dim 256 +2023-05-26 13:34:18 - SimpleLog - INFO: - critic_hidden_dim 256 +2023-05-26 13:34:18 - SimpleLog - INFO: - min_policy 0 +2023-05-26 13:34:18 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-05-26 13:34:18 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-05-26 13:34:18 - SimpleLog - INFO: - buffer_type ONPOLICY_QUE +2023-05-26 13:34:18 - SimpleLog - INFO: - buffer_size 100000 +2023-05-26 13:34:18 - SimpleLog - INFO: - epsilon_decay 500 +2023-05-26 13:34:18 - SimpleLog - INFO: - epsilon_end 0.01 +2023-05-26 13:34:18 - SimpleLog - INFO: - epsilon_start 0.95 +2023-05-26 13:34:18 - SimpleLog - INFO: - target_update 4 +2023-05-26 13:34:18 - SimpleLog - INFO: - ================================================================================ +2023-05-26 13:34:18 - SimpleLog - INFO: - Env Configs: +2023-05-26 13:34:18 - SimpleLog - INFO: - ================================================================================ +2023-05-26 13:34:18 - SimpleLog - INFO: - Name Value Type +2023-05-26 13:34:18 - SimpleLog - INFO: - id HalfCheetah-v4 +2023-05-26 13:34:18 - SimpleLog - INFO: - render_mode None +2023-05-26 13:34:18 - SimpleLog - INFO: - wrapper None +2023-05-26 13:34:18 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-05-26 13:34:18 - SimpleLog - INFO: - new_step_api 1 +2023-05-26 13:34:18 - SimpleLog - INFO: - ================================================================================ +2023-05-26 13:34:18 - SimpleLog - INFO: - obs_space: Box(-inf, inf, (17,), float64), n_actions: Box(-1.0, 1.0, (6,), float32) +2023-05-26 13:34:20 - SimpleLog - INFO: - Start training! +2023-05-26 13:34:23 - SimpleLog - INFO: - episode: 0, ep_reward: -353.4440298112672, ep_step: 1000 +2023-05-26 13:34:25 - SimpleLog - INFO: - episode: 1, ep_reward: -694.8368537149291, ep_step: 1000 +2023-05-26 13:34:26 - SimpleLog - INFO: - episode: 2, ep_reward: -481.95529377566396, ep_step: 1000 +2023-05-26 13:34:28 - SimpleLog - INFO: - episode: 3, ep_reward: -343.29053093187724, ep_step: 1000 +2023-05-26 13:34:30 - SimpleLog - INFO: - episode: 4, ep_reward: -164.8989985774828, ep_step: 1000 +2023-05-26 13:34:32 - SimpleLog - INFO: - episode: 5, ep_reward: -475.27449424703195, ep_step: 1000 +2023-05-26 13:34:33 - SimpleLog - INFO: - episode: 6, ep_reward: -231.44469619921054, ep_step: 1000 +2023-05-26 13:34:35 - SimpleLog - INFO: - episode: 7, ep_reward: -278.56920501383087, ep_step: 1000 +2023-05-26 13:34:37 - SimpleLog - INFO: - episode: 8, ep_reward: -352.67336520340217, ep_step: 1000 +2023-05-26 13:34:38 - SimpleLog - INFO: - episode: 9, ep_reward: -190.2866776404119, ep_step: 1000 +2023-05-26 13:34:40 - SimpleLog - INFO: - episode: 10, ep_reward: -304.1587664462243, ep_step: 1000 +2023-05-26 13:34:41 - SimpleLog - INFO: - episode: 11, ep_reward: -333.96271713860676, ep_step: 1000 +2023-05-26 13:34:43 - SimpleLog - INFO: - episode: 12, ep_reward: -283.0312428041367, ep_step: 1000 +2023-05-26 13:34:45 - SimpleLog - INFO: - episode: 13, ep_reward: -405.0291590821145, ep_step: 1000 +2023-05-26 13:34:46 - SimpleLog - INFO: - episode: 14, ep_reward: -214.1870201280391, ep_step: 1000 +2023-05-26 13:34:48 - SimpleLog - INFO: - episode: 15, ep_reward: -289.80674990922057, ep_step: 1000 +2023-05-26 13:34:50 - SimpleLog - INFO: - episode: 16, ep_reward: -236.38953454106945, ep_step: 1000 +2023-05-26 13:34:52 - SimpleLog - INFO: - episode: 17, ep_reward: -248.9777203817456, ep_step: 1000 +2023-05-26 13:34:54 - SimpleLog - INFO: - episode: 18, ep_reward: -261.6549035556871, ep_step: 1000 +2023-05-26 13:34:56 - SimpleLog - INFO: - episode: 19, ep_reward: -414.34261425658616, ep_step: 1000 +2023-05-26 13:34:58 - SimpleLog - INFO: - episode: 20, ep_reward: -313.5153835570287, ep_step: 1000 +2023-05-26 13:34:59 - SimpleLog - INFO: - episode: 21, ep_reward: -361.4715927146282, ep_step: 1000 +2023-05-26 13:35:01 - SimpleLog - INFO: - episode: 22, ep_reward: -286.55053726448403, ep_step: 1000 +2023-05-26 13:35:03 - SimpleLog - INFO: - episode: 23, ep_reward: -254.98711028510803, ep_step: 1000 +2023-05-26 13:35:04 - SimpleLog - INFO: - episode: 24, ep_reward: -308.80835330033415, ep_step: 1000 +2023-05-26 13:35:06 - SimpleLog - INFO: - episode: 25, ep_reward: -232.359041587131, ep_step: 1000 +2023-05-26 13:35:08 - SimpleLog - INFO: - episode: 26, ep_reward: -341.79180773637063, ep_step: 1000 +2023-05-26 13:35:10 - SimpleLog - INFO: - episode: 27, ep_reward: -216.03052457923567, ep_step: 1000 +2023-05-26 13:35:11 - SimpleLog - INFO: - episode: 28, ep_reward: -399.38958311019866, ep_step: 1000 +2023-05-26 13:35:13 - SimpleLog - INFO: - episode: 29, ep_reward: -209.10682908023696, ep_step: 1000 +2023-05-26 13:35:15 - SimpleLog - INFO: - episode: 30, ep_reward: -344.98447954117694, ep_step: 1000 +2023-05-26 13:35:17 - SimpleLog - INFO: - episode: 31, ep_reward: -287.85413978704673, ep_step: 1000 +2023-05-26 13:35:18 - SimpleLog - INFO: - episode: 32, ep_reward: -182.37840070399727, ep_step: 1000 +2023-05-26 13:35:20 - SimpleLog - INFO: - episode: 33, ep_reward: -156.95596980559418, ep_step: 1000 +2023-05-26 13:35:22 - SimpleLog - INFO: - episode: 34, ep_reward: -144.95451105234716, ep_step: 1000 +2023-05-26 13:35:23 - SimpleLog - INFO: - episode: 35, ep_reward: -191.46455898947684, ep_step: 1000 +2023-05-26 13:35:25 - SimpleLog - INFO: - episode: 36, ep_reward: -202.84799927473293, ep_step: 1000 +2023-05-26 13:35:27 - SimpleLog - INFO: - episode: 37, ep_reward: -98.52114346723053, ep_step: 1000 +2023-05-26 13:35:28 - SimpleLog - INFO: - episode: 38, ep_reward: -228.505897168364, ep_step: 1000 +2023-05-26 13:35:30 - SimpleLog - INFO: - episode: 39, ep_reward: -206.43609183256274, ep_step: 1000 +2023-05-26 13:35:32 - SimpleLog - INFO: - episode: 40, ep_reward: -177.80870955763626, ep_step: 1000 +2023-05-26 13:35:34 - SimpleLog - INFO: - episode: 41, ep_reward: -207.4418034873603, ep_step: 1000 +2023-05-26 13:35:35 - SimpleLog - INFO: - episode: 42, ep_reward: -226.44336539033876, ep_step: 1000 +2023-05-26 13:35:37 - SimpleLog - INFO: - episode: 43, ep_reward: -113.10462634764112, ep_step: 1000 +2023-05-26 13:35:39 - SimpleLog - INFO: - episode: 44, ep_reward: -211.45164658736073, ep_step: 1000 +2023-05-26 13:35:41 - SimpleLog - INFO: - episode: 45, ep_reward: -88.34496710646825, ep_step: 1000 +2023-05-26 13:35:42 - SimpleLog - INFO: - episode: 46, ep_reward: -15.633007029813944, ep_step: 1000 +2023-05-26 13:35:44 - SimpleLog - INFO: - episode: 47, ep_reward: -152.88452582688114, ep_step: 1000 +2023-05-26 13:35:46 - SimpleLog - INFO: - episode: 48, ep_reward: -261.52939204553087, ep_step: 1000 +2023-05-26 13:35:47 - SimpleLog - INFO: - episode: 49, ep_reward: -100.9454855180154, ep_step: 1000 +2023-05-26 13:35:49 - SimpleLog - INFO: - episode: 50, ep_reward: -405.9349939157042, ep_step: 1000 +2023-05-26 13:35:51 - SimpleLog - INFO: - episode: 51, ep_reward: -80.63743421537606, ep_step: 1000 +2023-05-26 13:35:53 - SimpleLog - INFO: - episode: 52, ep_reward: -156.50061105618667, ep_step: 1000 +2023-05-26 13:35:54 - SimpleLog - INFO: - episode: 53, ep_reward: -63.34070693939389, ep_step: 1000 +2023-05-26 13:35:56 - SimpleLog - INFO: - episode: 54, ep_reward: -97.21071262417401, ep_step: 1000 +2023-05-26 13:35:58 - SimpleLog - INFO: - episode: 55, ep_reward: -71.37454807231668, ep_step: 1000 +2023-05-26 13:36:00 - SimpleLog - INFO: - episode: 56, ep_reward: -133.22585740838312, ep_step: 1000 +2023-05-26 13:36:02 - SimpleLog - INFO: - episode: 57, ep_reward: -240.29407926776886, ep_step: 1000 +2023-05-26 13:36:04 - SimpleLog - INFO: - episode: 58, ep_reward: -58.56744339080999, ep_step: 1000 +2023-05-26 13:36:06 - SimpleLog - INFO: - episode: 59, ep_reward: -126.66373784837297, ep_step: 1000 +2023-05-26 13:36:07 - SimpleLog - INFO: - episode: 60, ep_reward: -115.30882593152718, ep_step: 1000 +2023-05-26 13:36:09 - SimpleLog - INFO: - episode: 61, ep_reward: -67.86974418388169, ep_step: 1000 +2023-05-26 13:36:11 - SimpleLog - INFO: - episode: 62, ep_reward: -142.55855013118207, ep_step: 1000 +2023-05-26 13:36:13 - SimpleLog - INFO: - episode: 63, ep_reward: -321.8517231318067, ep_step: 1000 +2023-05-26 13:36:14 - SimpleLog - INFO: - episode: 64, ep_reward: -180.40894564262396, ep_step: 1000 +2023-05-26 13:36:16 - SimpleLog - INFO: - episode: 65, ep_reward: -128.38952803370415, ep_step: 1000 +2023-05-26 13:36:18 - SimpleLog - INFO: - episode: 66, ep_reward: -144.84572465180756, ep_step: 1000 +2023-05-26 13:36:19 - SimpleLog - INFO: - episode: 67, ep_reward: -181.01384035532718, ep_step: 1000 +2023-05-26 13:36:21 - SimpleLog - INFO: - episode: 68, ep_reward: -221.89916065369374, ep_step: 1000 +2023-05-26 13:36:23 - SimpleLog - INFO: - episode: 69, ep_reward: -41.97370540441915, ep_step: 1000 +2023-05-26 13:36:25 - SimpleLog - INFO: - episode: 70, ep_reward: -19.479363790797343, ep_step: 1000 +2023-05-26 13:36:26 - SimpleLog - INFO: - episode: 71, ep_reward: -158.07911989329475, ep_step: 1000 +2023-05-26 13:36:28 - SimpleLog - INFO: - episode: 72, ep_reward: -134.8208870396498, ep_step: 1000 +2023-05-26 13:36:30 - SimpleLog - INFO: - episode: 73, ep_reward: -2.7171373156363403, ep_step: 1000 +2023-05-26 13:36:31 - SimpleLog - INFO: - episode: 74, ep_reward: -106.25619433289333, ep_step: 1000 +2023-05-26 13:36:33 - SimpleLog - INFO: - episode: 75, ep_reward: -76.39064953720792, ep_step: 1000 +2023-05-26 13:36:35 - SimpleLog - INFO: - episode: 76, ep_reward: -54.68020759698416, ep_step: 1000 +2023-05-26 13:36:37 - SimpleLog - INFO: - episode: 77, ep_reward: -244.5449328801806, ep_step: 1000 +2023-05-26 13:36:38 - SimpleLog - INFO: - episode: 78, ep_reward: -49.667758989766035, ep_step: 1000 +2023-05-26 13:36:40 - SimpleLog - INFO: - episode: 79, ep_reward: -1.4518721678767115, ep_step: 1000 +2023-05-26 13:36:42 - SimpleLog - INFO: - episode: 80, ep_reward: -70.54114256399173, ep_step: 1000 +2023-05-26 13:36:43 - SimpleLog - INFO: - episode: 81, ep_reward: -69.69994649541124, ep_step: 1000 +2023-05-26 13:36:45 - SimpleLog - INFO: - episode: 82, ep_reward: -153.69741354110286, ep_step: 1000 +2023-05-26 13:36:47 - SimpleLog - INFO: - episode: 83, ep_reward: -77.30010467579783, ep_step: 1000 +2023-05-26 13:36:48 - SimpleLog - INFO: - episode: 84, ep_reward: -118.18698313537638, ep_step: 1000 +2023-05-26 13:36:50 - SimpleLog - INFO: - episode: 85, ep_reward: -124.83829187349701, ep_step: 1000 +2023-05-26 13:36:52 - SimpleLog - INFO: - episode: 86, ep_reward: 42.19629927629477, ep_step: 1000 +2023-05-26 13:36:54 - SimpleLog - INFO: - episode: 87, ep_reward: -146.25285012970377, ep_step: 1000 +2023-05-26 13:36:55 - SimpleLog - INFO: - episode: 88, ep_reward: -136.4419658347794, ep_step: 1000 +2023-05-26 13:36:57 - SimpleLog - INFO: - episode: 89, ep_reward: 58.99433961451249, ep_step: 1000 +2023-05-26 13:36:59 - SimpleLog - INFO: - episode: 90, ep_reward: 78.76197369149725, ep_step: 1000 +2023-05-26 13:37:00 - SimpleLog - INFO: - episode: 91, ep_reward: -29.41686308869272, ep_step: 1000 +2023-05-26 13:37:02 - SimpleLog - INFO: - episode: 92, ep_reward: -131.16829191696243, ep_step: 1000 +2023-05-26 13:37:04 - SimpleLog - INFO: - episode: 93, ep_reward: 3.760626470347165, ep_step: 1000 +2023-05-26 13:37:06 - SimpleLog - INFO: - episode: 94, ep_reward: 3.1548153449797938, ep_step: 1000 +2023-05-26 13:37:07 - SimpleLog - INFO: - episode: 95, ep_reward: -80.26092811507563, ep_step: 1000 +2023-05-26 13:37:09 - SimpleLog - INFO: - episode: 96, ep_reward: -94.71303008586766, ep_step: 1000 +2023-05-26 13:37:11 - SimpleLog - INFO: - episode: 97, ep_reward: -145.29548000585086, ep_step: 1000 +2023-05-26 13:37:13 - SimpleLog - INFO: - episode: 98, ep_reward: -41.773175492655824, ep_step: 1000 +2023-05-26 13:37:14 - SimpleLog - INFO: - episode: 99, ep_reward: -56.03373652870542, ep_step: 1000 +2023-05-26 13:37:16 - SimpleLog - INFO: - episode: 100, ep_reward: -68.44187676330561, ep_step: 1000 +2023-05-26 13:37:18 - SimpleLog - INFO: - episode: 101, ep_reward: 51.64587358530625, ep_step: 1000 +2023-05-26 13:37:19 - SimpleLog - INFO: - episode: 102, ep_reward: -79.09023255042999, ep_step: 1000 +2023-05-26 13:37:21 - SimpleLog - INFO: - episode: 103, ep_reward: -25.600762486465236, ep_step: 1000 +2023-05-26 13:37:23 - SimpleLog - INFO: - episode: 104, ep_reward: -1.5257060204140585, ep_step: 1000 +2023-05-26 13:37:24 - SimpleLog - INFO: - episode: 105, ep_reward: 27.022694865105812, ep_step: 1000 +2023-05-26 13:37:26 - SimpleLog - INFO: - episode: 106, ep_reward: -156.51758878137505, ep_step: 1000 +2023-05-26 13:37:28 - SimpleLog - INFO: - episode: 107, ep_reward: -19.97173206525022, ep_step: 1000 +2023-05-26 13:37:30 - SimpleLog - INFO: - episode: 108, ep_reward: -50.349439412585646, ep_step: 1000 +2023-05-26 13:37:31 - SimpleLog - INFO: - episode: 109, ep_reward: 24.79802039400801, ep_step: 1000 +2023-05-26 13:37:33 - SimpleLog - INFO: - episode: 110, ep_reward: 88.60745268603495, ep_step: 1000 +2023-05-26 13:37:35 - SimpleLog - INFO: - episode: 111, ep_reward: -60.81557611739857, ep_step: 1000 +2023-05-26 13:37:36 - SimpleLog - INFO: - episode: 112, ep_reward: -62.9899710937406, ep_step: 1000 +2023-05-26 13:37:38 - SimpleLog - INFO: - episode: 113, ep_reward: -72.69248004312749, ep_step: 1000 +2023-05-26 13:37:40 - SimpleLog - INFO: - episode: 114, ep_reward: 3.5072393258132326, ep_step: 1000 +2023-05-26 13:37:42 - SimpleLog - INFO: - episode: 115, ep_reward: -51.608381606515024, ep_step: 1000 +2023-05-26 13:37:43 - SimpleLog - INFO: - episode: 116, ep_reward: -37.673355604174844, ep_step: 1000 +2023-05-26 13:37:45 - SimpleLog - INFO: - episode: 117, ep_reward: -42.77020642157073, ep_step: 1000 +2023-05-26 13:37:47 - SimpleLog - INFO: - episode: 118, ep_reward: 176.8251028699036, ep_step: 1000 +2023-05-26 13:37:48 - SimpleLog - INFO: - episode: 119, ep_reward: -73.1298736767802, ep_step: 1000 +2023-05-26 13:37:50 - SimpleLog - INFO: - episode: 120, ep_reward: -84.61322046309644, ep_step: 1000 +2023-05-26 13:37:52 - SimpleLog - INFO: - episode: 121, ep_reward: -133.1374531071011, ep_step: 1000 +2023-05-26 13:37:54 - SimpleLog - INFO: - episode: 122, ep_reward: -43.56835842284387, ep_step: 1000 +2023-05-26 13:37:55 - SimpleLog - INFO: - episode: 123, ep_reward: 44.62207575831097, ep_step: 1000 +2023-05-26 13:37:57 - SimpleLog - INFO: - episode: 124, ep_reward: -19.268621911447482, ep_step: 1000 +2023-05-26 13:37:59 - SimpleLog - INFO: - episode: 125, ep_reward: -94.96155674032552, ep_step: 1000 +2023-05-26 13:38:01 - SimpleLog - INFO: - episode: 126, ep_reward: -109.57722555144397, ep_step: 1000 +2023-05-26 13:38:08 - SimpleLog - INFO: - update_step: 500, online_eval_reward: 495.256 +2023-05-26 13:38:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 495.256, save the best model! +2023-05-26 13:38:08 - SimpleLog - INFO: - episode: 127, ep_reward: -30.942134375756194, ep_step: 1000 +2023-05-26 13:38:09 - SimpleLog - INFO: - episode: 128, ep_reward: -73.44427584275432, ep_step: 1000 +2023-05-26 13:38:11 - SimpleLog - INFO: - episode: 129, ep_reward: 14.643620070223648, ep_step: 1000 +2023-05-26 13:38:13 - SimpleLog - INFO: - episode: 130, ep_reward: 99.89993207957265, ep_step: 1000 +2023-05-26 13:38:15 - SimpleLog - INFO: - episode: 131, ep_reward: 44.32360071367183, ep_step: 1000 +2023-05-26 13:38:16 - SimpleLog - INFO: - episode: 132, ep_reward: -28.713224610978838, ep_step: 1000 +2023-05-26 13:38:18 - SimpleLog - INFO: - episode: 133, ep_reward: 166.60372348427893, ep_step: 1000 +2023-05-26 13:38:20 - SimpleLog - INFO: - episode: 134, ep_reward: 76.20555034252654, ep_step: 1000 +2023-05-26 13:38:22 - SimpleLog - INFO: - episode: 135, ep_reward: 87.13526341662747, ep_step: 1000 +2023-05-26 13:38:24 - SimpleLog - INFO: - episode: 136, ep_reward: 48.83886978844659, ep_step: 1000 +2023-05-26 13:38:26 - SimpleLog - INFO: - episode: 137, ep_reward: -60.195985606538116, ep_step: 1000 +2023-05-26 13:38:27 - SimpleLog - INFO: - episode: 138, ep_reward: 86.40631306164423, ep_step: 1000 +2023-05-26 13:38:29 - SimpleLog - INFO: - episode: 139, ep_reward: -93.08984286607148, ep_step: 1000 +2023-05-26 13:38:31 - SimpleLog - INFO: - episode: 140, ep_reward: -49.26471640862492, ep_step: 1000 +2023-05-26 13:38:33 - SimpleLog - INFO: - episode: 141, ep_reward: -118.44730824016955, ep_step: 1000 +2023-05-26 13:38:34 - SimpleLog - INFO: - episode: 142, ep_reward: -49.30511093115162, ep_step: 1000 +2023-05-26 13:38:36 - SimpleLog - INFO: - episode: 143, ep_reward: -63.709663756643515, ep_step: 1000 +2023-05-26 13:38:38 - SimpleLog - INFO: - episode: 144, ep_reward: -185.61241091590733, ep_step: 1000 +2023-05-26 13:38:40 - SimpleLog - INFO: - episode: 145, ep_reward: -22.838154074612632, ep_step: 1000 +2023-05-26 13:38:41 - SimpleLog - INFO: - episode: 146, ep_reward: 26.79093468034007, ep_step: 1000 +2023-05-26 13:38:43 - SimpleLog - INFO: - episode: 147, ep_reward: -53.6534708839841, ep_step: 1000 +2023-05-26 13:38:45 - SimpleLog - INFO: - episode: 148, ep_reward: 202.90784454260367, ep_step: 1000 +2023-05-26 13:38:46 - SimpleLog - INFO: - episode: 149, ep_reward: 137.66372903175846, ep_step: 1000 +2023-05-26 13:38:48 - SimpleLog - INFO: - episode: 150, ep_reward: 63.020622022801206, ep_step: 1000 +2023-05-26 13:38:49 - SimpleLog - INFO: - episode: 151, ep_reward: -23.32292279991932, ep_step: 1000 +2023-05-26 13:38:51 - SimpleLog - INFO: - episode: 152, ep_reward: -1.7111032983489758, ep_step: 1000 +2023-05-26 13:38:53 - SimpleLog - INFO: - episode: 153, ep_reward: -53.920871010961925, ep_step: 1000 +2023-05-26 13:38:54 - SimpleLog - INFO: - episode: 154, ep_reward: 6.976887117264625, ep_step: 1000 +2023-05-26 13:38:56 - SimpleLog - INFO: - episode: 155, ep_reward: 89.30892099002239, ep_step: 1000 +2023-05-26 13:38:58 - SimpleLog - INFO: - episode: 156, ep_reward: 124.01719972461147, ep_step: 1000 +2023-05-26 13:38:59 - SimpleLog - INFO: - episode: 157, ep_reward: 8.563440782991728, ep_step: 1000 +2023-05-26 13:39:01 - SimpleLog - INFO: - episode: 158, ep_reward: 5.043601543158411, ep_step: 1000 +2023-05-26 13:39:03 - SimpleLog - INFO: - episode: 159, ep_reward: 67.90336158699844, ep_step: 1000 +2023-05-26 13:39:04 - SimpleLog - INFO: - episode: 160, ep_reward: -40.03214516553503, ep_step: 1000 +2023-05-26 13:39:06 - SimpleLog - INFO: - episode: 161, ep_reward: 49.607280355415895, ep_step: 1000 +2023-05-26 13:39:08 - SimpleLog - INFO: - episode: 162, ep_reward: -25.815730916520618, ep_step: 1000 +2023-05-26 13:39:09 - SimpleLog - INFO: - episode: 163, ep_reward: 102.80106339062156, ep_step: 1000 +2023-05-26 13:39:11 - SimpleLog - INFO: - episode: 164, ep_reward: 59.39889285074115, ep_step: 1000 +2023-05-26 13:39:13 - SimpleLog - INFO: - episode: 165, ep_reward: 177.21785420658446, ep_step: 1000 +2023-05-26 13:39:15 - SimpleLog - INFO: - episode: 166, ep_reward: 130.269913399386, ep_step: 1000 +2023-05-26 13:39:17 - SimpleLog - INFO: - episode: 167, ep_reward: 108.21512777725559, ep_step: 1000 +2023-05-26 13:39:19 - SimpleLog - INFO: - episode: 168, ep_reward: -16.209228217935074, ep_step: 1000 +2023-05-26 13:39:21 - SimpleLog - INFO: - episode: 169, ep_reward: -11.462412494236874, ep_step: 1000 +2023-05-26 13:39:22 - SimpleLog - INFO: - episode: 170, ep_reward: 146.17490097888037, ep_step: 1000 +2023-05-26 13:39:24 - SimpleLog - INFO: - episode: 171, ep_reward: 74.23058028055341, ep_step: 1000 +2023-05-26 13:39:26 - SimpleLog - INFO: - episode: 172, ep_reward: 33.585604501882905, ep_step: 1000 +2023-05-26 13:39:28 - SimpleLog - INFO: - episode: 173, ep_reward: 60.87544290851755, ep_step: 1000 +2023-05-26 13:39:29 - SimpleLog - INFO: - episode: 174, ep_reward: 36.752916888381144, ep_step: 1000 +2023-05-26 13:39:31 - SimpleLog - INFO: - episode: 175, ep_reward: 21.098480107989296, ep_step: 1000 +2023-05-26 13:39:33 - SimpleLog - INFO: - episode: 176, ep_reward: 56.26313209275936, ep_step: 1000 +2023-05-26 13:39:35 - SimpleLog - INFO: - episode: 177, ep_reward: 86.11833704850046, ep_step: 1000 +2023-05-26 13:39:37 - SimpleLog - INFO: - episode: 178, ep_reward: 45.97929654620022, ep_step: 1000 +2023-05-26 13:39:38 - SimpleLog - INFO: - episode: 179, ep_reward: 92.05714993822815, ep_step: 1000 +2023-05-26 13:39:40 - SimpleLog - INFO: - episode: 180, ep_reward: 41.70548097510302, ep_step: 1000 +2023-05-26 13:39:42 - SimpleLog - INFO: - episode: 181, ep_reward: 27.598280194138734, ep_step: 1000 +2023-05-26 13:39:43 - SimpleLog - INFO: - episode: 182, ep_reward: 35.084171140701756, ep_step: 1000 +2023-05-26 13:39:45 - SimpleLog - INFO: - episode: 183, ep_reward: 237.71514418015323, ep_step: 1000 +2023-05-26 13:39:47 - SimpleLog - INFO: - episode: 184, ep_reward: 96.26607529720056, ep_step: 1000 +2023-05-26 13:39:49 - SimpleLog - INFO: - episode: 185, ep_reward: 33.358637149854495, ep_step: 1000 +2023-05-26 13:39:50 - SimpleLog - INFO: - episode: 186, ep_reward: 4.45270260550742, ep_step: 1000 +2023-05-26 13:39:52 - SimpleLog - INFO: - episode: 187, ep_reward: 197.127726150224, ep_step: 1000 +2023-05-26 13:39:54 - SimpleLog - INFO: - episode: 188, ep_reward: 119.33925627569441, ep_step: 1000 +2023-05-26 13:39:56 - SimpleLog - INFO: - episode: 189, ep_reward: 86.98830922411267, ep_step: 1000 +2023-05-26 13:39:57 - SimpleLog - INFO: - episode: 190, ep_reward: 119.20106060728826, ep_step: 1000 +2023-05-26 13:39:59 - SimpleLog - INFO: - episode: 191, ep_reward: 108.72417359745833, ep_step: 1000 +2023-05-26 13:40:01 - SimpleLog - INFO: - episode: 192, ep_reward: 23.56214523351796, ep_step: 1000 +2023-05-26 13:40:03 - SimpleLog - INFO: - episode: 193, ep_reward: 189.01375758399524, ep_step: 1000 +2023-05-26 13:40:04 - SimpleLog - INFO: - episode: 194, ep_reward: 95.22584205914174, ep_step: 1000 +2023-05-26 13:40:06 - SimpleLog - INFO: - episode: 195, ep_reward: 131.83128559757253, ep_step: 1000 +2023-05-26 13:40:08 - SimpleLog - INFO: - episode: 196, ep_reward: 127.09510992791333, ep_step: 1000 +2023-05-26 13:40:09 - SimpleLog - INFO: - episode: 197, ep_reward: 195.67432198367095, ep_step: 1000 +2023-05-26 13:40:11 - SimpleLog - INFO: - episode: 198, ep_reward: 147.59125569415238, ep_step: 1000 +2023-05-26 13:40:13 - SimpleLog - INFO: - episode: 199, ep_reward: 237.4057869743553, ep_step: 1000 +2023-05-26 13:40:14 - SimpleLog - INFO: - episode: 200, ep_reward: 279.8075162308726, ep_step: 1000 +2023-05-26 13:40:16 - SimpleLog - INFO: - episode: 201, ep_reward: 65.78130423988176, ep_step: 1000 +2023-05-26 13:40:18 - SimpleLog - INFO: - episode: 202, ep_reward: 153.65510274813298, ep_step: 1000 +2023-05-26 13:40:20 - SimpleLog - INFO: - episode: 203, ep_reward: 236.08436219365134, ep_step: 1000 +2023-05-26 13:40:21 - SimpleLog - INFO: - episode: 204, ep_reward: 111.68838574498187, ep_step: 1000 +2023-05-26 13:40:23 - SimpleLog - INFO: - episode: 205, ep_reward: 70.22133195429603, ep_step: 1000 +2023-05-26 13:40:25 - SimpleLog - INFO: - episode: 206, ep_reward: 101.46539336853397, ep_step: 1000 +2023-05-26 13:40:27 - SimpleLog - INFO: - episode: 207, ep_reward: 210.30445063778933, ep_step: 1000 +2023-05-26 13:40:29 - SimpleLog - INFO: - episode: 208, ep_reward: 215.42189752571124, ep_step: 1000 +2023-05-26 13:40:31 - SimpleLog - INFO: - episode: 209, ep_reward: 9.453197233012265, ep_step: 1000 +2023-05-26 13:40:33 - SimpleLog - INFO: - episode: 210, ep_reward: 199.99930432762918, ep_step: 1000 +2023-05-26 13:40:35 - SimpleLog - INFO: - episode: 211, ep_reward: 138.93852220479135, ep_step: 1000 +2023-05-26 13:40:36 - SimpleLog - INFO: - episode: 212, ep_reward: 175.5833791561973, ep_step: 1000 +2023-05-26 13:40:38 - SimpleLog - INFO: - episode: 213, ep_reward: 197.2489412918545, ep_step: 1000 +2023-05-26 13:40:39 - SimpleLog - INFO: - episode: 214, ep_reward: 55.09578219691432, ep_step: 1000 +2023-05-26 13:40:41 - SimpleLog - INFO: - episode: 215, ep_reward: 109.08714818616812, ep_step: 1000 +2023-05-26 13:40:43 - SimpleLog - INFO: - episode: 216, ep_reward: 213.9792207771918, ep_step: 1000 +2023-05-26 13:40:45 - SimpleLog - INFO: - episode: 217, ep_reward: 124.35651096118029, ep_step: 1000 +2023-05-26 13:40:46 - SimpleLog - INFO: - episode: 218, ep_reward: 285.78676570087026, ep_step: 1000 +2023-05-26 13:40:48 - SimpleLog - INFO: - episode: 219, ep_reward: 244.31414727534954, ep_step: 1000 +2023-05-26 13:40:49 - SimpleLog - INFO: - episode: 220, ep_reward: 104.64074864359866, ep_step: 1000 +2023-05-26 13:40:52 - SimpleLog - INFO: - episode: 221, ep_reward: 86.93409462795906, ep_step: 1000 +2023-05-26 13:40:53 - SimpleLog - INFO: - episode: 222, ep_reward: 177.47091939748705, ep_step: 1000 +2023-05-26 13:40:55 - SimpleLog - INFO: - episode: 223, ep_reward: 210.9915083791763, ep_step: 1000 +2023-05-26 13:40:57 - SimpleLog - INFO: - episode: 224, ep_reward: 205.47699029224032, ep_step: 1000 +2023-05-26 13:40:58 - SimpleLog - INFO: - episode: 225, ep_reward: 184.361208527488, ep_step: 1000 +2023-05-26 13:41:00 - SimpleLog - INFO: - episode: 226, ep_reward: -62.95498885358335, ep_step: 1000 +2023-05-26 13:41:02 - SimpleLog - INFO: - episode: 227, ep_reward: 22.575470294714304, ep_step: 1000 +2023-05-26 13:41:03 - SimpleLog - INFO: - episode: 228, ep_reward: 211.14584668400124, ep_step: 1000 +2023-05-26 13:41:05 - SimpleLog - INFO: - episode: 229, ep_reward: 116.51013781983565, ep_step: 1000 +2023-05-26 13:41:07 - SimpleLog - INFO: - episode: 230, ep_reward: 85.52952068620256, ep_step: 1000 +2023-05-26 13:41:09 - SimpleLog - INFO: - episode: 231, ep_reward: 253.0291108798236, ep_step: 1000 +2023-05-26 13:41:11 - SimpleLog - INFO: - episode: 232, ep_reward: 204.35149855083893, ep_step: 1000 +2023-05-26 13:41:12 - SimpleLog - INFO: - episode: 233, ep_reward: -80.31551289111532, ep_step: 1000 +2023-05-26 13:41:14 - SimpleLog - INFO: - episode: 234, ep_reward: 245.4551803371105, ep_step: 1000 +2023-05-26 13:41:16 - SimpleLog - INFO: - episode: 235, ep_reward: 175.24876013875098, ep_step: 1000 +2023-05-26 13:41:17 - SimpleLog - INFO: - episode: 236, ep_reward: 57.7012885585139, ep_step: 1000 +2023-05-26 13:41:19 - SimpleLog - INFO: - episode: 237, ep_reward: 259.50044826240327, ep_step: 1000 +2023-05-26 13:41:21 - SimpleLog - INFO: - episode: 238, ep_reward: -91.62111619119958, ep_step: 1000 +2023-05-26 13:41:23 - SimpleLog - INFO: - episode: 239, ep_reward: 89.63973944216872, ep_step: 1000 +2023-05-26 13:41:25 - SimpleLog - INFO: - episode: 240, ep_reward: 301.5887638634141, ep_step: 1000 +2023-05-26 13:41:26 - SimpleLog - INFO: - episode: 241, ep_reward: 249.11052780272533, ep_step: 1000 +2023-05-26 13:41:28 - SimpleLog - INFO: - episode: 242, ep_reward: 59.3447697951206, ep_step: 1000 +2023-05-26 13:41:30 - SimpleLog - INFO: - episode: 243, ep_reward: -25.923987064022604, ep_step: 1000 +2023-05-26 13:41:32 - SimpleLog - INFO: - episode: 244, ep_reward: 147.50919244693517, ep_step: 1000 +2023-05-26 13:41:34 - SimpleLog - INFO: - episode: 245, ep_reward: 99.17246247040059, ep_step: 1000 +2023-05-26 13:41:36 - SimpleLog - INFO: - episode: 246, ep_reward: 162.52976888174476, ep_step: 1000 +2023-05-26 13:41:38 - SimpleLog - INFO: - episode: 247, ep_reward: 29.67403221188573, ep_step: 1000 +2023-05-26 13:41:40 - SimpleLog - INFO: - episode: 248, ep_reward: 114.73874775003561, ep_step: 1000 +2023-05-26 13:41:41 - SimpleLog - INFO: - episode: 249, ep_reward: -3.6670995425247774, ep_step: 1000 +2023-05-26 13:41:43 - SimpleLog - INFO: - episode: 250, ep_reward: 87.82467448355746, ep_step: 1000 +2023-05-26 13:41:45 - SimpleLog - INFO: - episode: 251, ep_reward: -120.42543537527735, ep_step: 1000 +2023-05-26 13:41:46 - SimpleLog - INFO: - episode: 252, ep_reward: 222.95853520952244, ep_step: 1000 +2023-05-26 13:41:48 - SimpleLog - INFO: - episode: 253, ep_reward: 219.90696727353514, ep_step: 1000 +2023-05-26 13:41:50 - SimpleLog - INFO: - episode: 254, ep_reward: -19.00245171882298, ep_step: 1000 +2023-05-26 13:41:57 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: 350.632 +2023-05-26 13:41:57 - SimpleLog - INFO: - episode: 255, ep_reward: 202.50179876549598, ep_step: 1000 +2023-05-26 13:41:58 - SimpleLog - INFO: - episode: 256, ep_reward: -176.53904206433438, ep_step: 1000 +2023-05-26 13:41:59 - SimpleLog - INFO: - episode: 257, ep_reward: 13.878272297268788, ep_step: 1000 +2023-05-26 13:42:01 - SimpleLog - INFO: - episode: 258, ep_reward: 125.25046725897936, ep_step: 1000 +2023-05-26 13:42:02 - SimpleLog - INFO: - episode: 259, ep_reward: 67.90546375929473, ep_step: 1000 +2023-05-26 13:42:03 - SimpleLog - INFO: - episode: 260, ep_reward: 234.42046688633116, ep_step: 1000 +2023-05-26 13:42:05 - SimpleLog - INFO: - episode: 261, ep_reward: 151.91268643694698, ep_step: 1000 +2023-05-26 13:42:06 - SimpleLog - INFO: - episode: 262, ep_reward: 138.32741782586177, ep_step: 1000 +2023-05-26 13:42:08 - SimpleLog - INFO: - episode: 263, ep_reward: 121.69281623014551, ep_step: 1000 +2023-05-26 13:42:10 - SimpleLog - INFO: - episode: 264, ep_reward: 10.473420543016607, ep_step: 1000 +2023-05-26 13:42:11 - SimpleLog - INFO: - episode: 265, ep_reward: 139.96563756884038, ep_step: 1000 +2023-05-26 13:42:13 - SimpleLog - INFO: - episode: 266, ep_reward: 126.00626561113955, ep_step: 1000 +2023-05-26 13:42:14 - SimpleLog - INFO: - episode: 267, ep_reward: 96.64275846306245, ep_step: 1000 +2023-05-26 13:42:16 - SimpleLog - INFO: - episode: 268, ep_reward: -75.04130836151505, ep_step: 1000 +2023-05-26 13:42:18 - SimpleLog - INFO: - episode: 269, ep_reward: 207.7345564175367, ep_step: 1000 +2023-05-26 13:42:20 - SimpleLog - INFO: - episode: 270, ep_reward: 33.16502440038516, ep_step: 1000 +2023-05-26 13:42:21 - SimpleLog - INFO: - episode: 271, ep_reward: 177.93200428006753, ep_step: 1000 +2023-05-26 13:42:23 - SimpleLog - INFO: - episode: 272, ep_reward: 322.14063327112535, ep_step: 1000 +2023-05-26 13:42:25 - SimpleLog - INFO: - episode: 273, ep_reward: 262.0289773182554, ep_step: 1000 +2023-05-26 13:42:26 - SimpleLog - INFO: - episode: 274, ep_reward: 28.475467641363416, ep_step: 1000 +2023-05-26 13:42:28 - SimpleLog - INFO: - episode: 275, ep_reward: 325.3436752824176, ep_step: 1000 +2023-05-26 13:42:30 - SimpleLog - INFO: - episode: 276, ep_reward: 245.44549725330018, ep_step: 1000 +2023-05-26 13:42:31 - SimpleLog - INFO: - episode: 277, ep_reward: -153.92647497820013, ep_step: 1000 +2023-05-26 13:42:33 - SimpleLog - INFO: - episode: 278, ep_reward: 107.13613903753073, ep_step: 1000 +2023-05-26 13:42:35 - SimpleLog - INFO: - episode: 279, ep_reward: 291.57819857283516, ep_step: 1000 +2023-05-26 13:42:37 - SimpleLog - INFO: - episode: 280, ep_reward: 304.8307125988563, ep_step: 1000 +2023-05-26 13:42:39 - SimpleLog - INFO: - episode: 281, ep_reward: -10.020069951214955, ep_step: 1000 +2023-05-26 13:42:41 - SimpleLog - INFO: - episode: 282, ep_reward: 200.10424282109383, ep_step: 1000 +2023-05-26 13:42:43 - SimpleLog - INFO: - episode: 283, ep_reward: -118.36614651787994, ep_step: 1000 +2023-05-26 13:42:45 - SimpleLog - INFO: - episode: 284, ep_reward: 84.89214464892538, ep_step: 1000 +2023-05-26 13:42:46 - SimpleLog - INFO: - episode: 285, ep_reward: 87.29079211549214, ep_step: 1000 +2023-05-26 13:42:48 - SimpleLog - INFO: - episode: 286, ep_reward: -58.80671506043301, ep_step: 1000 +2023-05-26 13:42:50 - SimpleLog - INFO: - episode: 287, ep_reward: 173.56160935684514, ep_step: 1000 +2023-05-26 13:42:51 - SimpleLog - INFO: - episode: 288, ep_reward: -135.61728882531756, ep_step: 1000 +2023-05-26 13:42:53 - SimpleLog - INFO: - episode: 289, ep_reward: 162.4167151204706, ep_step: 1000 +2023-05-26 13:42:55 - SimpleLog - INFO: - episode: 290, ep_reward: -241.18742316027672, ep_step: 1000 +2023-05-26 13:42:57 - SimpleLog - INFO: - episode: 291, ep_reward: -258.40134602719104, ep_step: 1000 +2023-05-26 13:42:58 - SimpleLog - INFO: - episode: 292, ep_reward: 35.11286540925905, ep_step: 1000 +2023-05-26 13:43:00 - SimpleLog - INFO: - episode: 293, ep_reward: -15.66444216899099, ep_step: 1000 +2023-05-26 13:43:02 - SimpleLog - INFO: - episode: 294, ep_reward: -333.53213645122344, ep_step: 1000 +2023-05-26 13:43:04 - SimpleLog - INFO: - episode: 295, ep_reward: -571.2690925414367, ep_step: 1000 +2023-05-26 13:43:05 - SimpleLog - INFO: - episode: 296, ep_reward: -579.091001730847, ep_step: 1000 +2023-05-26 13:43:07 - SimpleLog - INFO: - episode: 297, ep_reward: 145.45436848779627, ep_step: 1000 +2023-05-26 13:43:09 - SimpleLog - INFO: - episode: 298, ep_reward: 86.22172642465283, ep_step: 1000 +2023-05-26 13:43:11 - SimpleLog - INFO: - episode: 299, ep_reward: 5.805481992674584, ep_step: 1000 +2023-05-26 13:43:12 - SimpleLog - INFO: - episode: 300, ep_reward: 31.686826575681977, ep_step: 1000 +2023-05-26 13:43:14 - SimpleLog - INFO: - episode: 301, ep_reward: -77.17002846026715, ep_step: 1000 +2023-05-26 13:43:16 - SimpleLog - INFO: - episode: 302, ep_reward: -91.66700597546857, ep_step: 1000 +2023-05-26 13:43:17 - SimpleLog - INFO: - episode: 303, ep_reward: -67.31776650705193, ep_step: 1000 +2023-05-26 13:43:19 - SimpleLog - INFO: - episode: 304, ep_reward: -20.44851275358667, ep_step: 1000 +2023-05-26 13:43:21 - SimpleLog - INFO: - episode: 305, ep_reward: -98.39173195187867, ep_step: 1000 +2023-05-26 13:43:22 - SimpleLog - INFO: - episode: 306, ep_reward: -0.340974207767035, ep_step: 1000 +2023-05-26 13:43:24 - SimpleLog - INFO: - episode: 307, ep_reward: 33.61302419242136, ep_step: 1000 +2023-05-26 13:43:26 - SimpleLog - INFO: - episode: 308, ep_reward: 74.08551393800595, ep_step: 1000 +2023-05-26 13:43:28 - SimpleLog - INFO: - episode: 309, ep_reward: 131.9091413877136, ep_step: 1000 +2023-05-26 13:43:29 - SimpleLog - INFO: - episode: 310, ep_reward: 67.85317995408774, ep_step: 1000 +2023-05-26 13:43:31 - SimpleLog - INFO: - episode: 311, ep_reward: 209.22494119960828, ep_step: 1000 +2023-05-26 13:43:33 - SimpleLog - INFO: - episode: 312, ep_reward: 200.54856241010592, ep_step: 1000 +2023-05-26 13:43:34 - SimpleLog - INFO: - episode: 313, ep_reward: 176.94803875935807, ep_step: 1000 +2023-05-26 13:43:36 - SimpleLog - INFO: - episode: 314, ep_reward: 218.85333053385023, ep_step: 1000 +2023-05-26 13:43:38 - SimpleLog - INFO: - episode: 315, ep_reward: 183.9465133316433, ep_step: 1000 +2023-05-26 13:43:40 - SimpleLog - INFO: - episode: 316, ep_reward: 231.81190852885823, ep_step: 1000 +2023-05-26 13:43:42 - SimpleLog - INFO: - episode: 317, ep_reward: 176.77118005214587, ep_step: 1000 +2023-05-26 13:43:44 - SimpleLog - INFO: - episode: 318, ep_reward: 241.8535214742748, ep_step: 1000 +2023-05-26 13:43:45 - SimpleLog - INFO: - episode: 319, ep_reward: 175.56269931467563, ep_step: 1000 +2023-05-26 13:43:47 - SimpleLog - INFO: - episode: 320, ep_reward: 155.78849638222545, ep_step: 1000 +2023-05-26 13:43:49 - SimpleLog - INFO: - episode: 321, ep_reward: -119.47003151460645, ep_step: 1000 +2023-05-26 13:43:51 - SimpleLog - INFO: - episode: 322, ep_reward: -293.87223603817387, ep_step: 1000 +2023-05-26 13:43:52 - SimpleLog - INFO: - episode: 323, ep_reward: 239.9354143207326, ep_step: 1000 +2023-05-26 13:43:54 - SimpleLog - INFO: - episode: 324, ep_reward: 39.04379757265415, ep_step: 1000 +2023-05-26 13:43:56 - SimpleLog - INFO: - episode: 325, ep_reward: 49.38318347722066, ep_step: 1000 +2023-05-26 13:43:58 - SimpleLog - INFO: - episode: 326, ep_reward: 241.02801899599294, ep_step: 1000 +2023-05-26 13:44:00 - SimpleLog - INFO: - episode: 327, ep_reward: 227.65899152104674, ep_step: 1000 +2023-05-26 13:44:01 - SimpleLog - INFO: - episode: 328, ep_reward: 169.03971735655344, ep_step: 1000 +2023-05-26 13:44:03 - SimpleLog - INFO: - episode: 329, ep_reward: 32.132710545366365, ep_step: 1000 +2023-05-26 13:44:05 - SimpleLog - INFO: - episode: 330, ep_reward: 244.99947034049762, ep_step: 1000 +2023-05-26 13:44:06 - SimpleLog - INFO: - episode: 331, ep_reward: -49.960707369428775, ep_step: 1000 +2023-05-26 13:44:08 - SimpleLog - INFO: - episode: 332, ep_reward: 129.8087050694714, ep_step: 1000 +2023-05-26 13:44:10 - SimpleLog - INFO: - episode: 333, ep_reward: 158.9896891616816, ep_step: 1000 +2023-05-26 13:44:12 - SimpleLog - INFO: - episode: 334, ep_reward: 18.058124127547277, ep_step: 1000 +2023-05-26 13:44:14 - SimpleLog - INFO: - episode: 335, ep_reward: -20.184554148641613, ep_step: 1000 +2023-05-26 13:44:15 - SimpleLog - INFO: - episode: 336, ep_reward: 118.80591506208995, ep_step: 1000 +2023-05-26 13:44:17 - SimpleLog - INFO: - episode: 337, ep_reward: 95.72957010908125, ep_step: 1000 +2023-05-26 13:44:19 - SimpleLog - INFO: - episode: 338, ep_reward: 131.3397785188506, ep_step: 1000 +2023-05-26 13:44:20 - SimpleLog - INFO: - episode: 339, ep_reward: 91.50727925000704, ep_step: 1000 +2023-05-26 13:44:22 - SimpleLog - INFO: - episode: 340, ep_reward: 324.3779193188042, ep_step: 1000 +2023-05-26 13:44:24 - SimpleLog - INFO: - episode: 341, ep_reward: 273.26867999665524, ep_step: 1000 +2023-05-26 13:44:26 - SimpleLog - INFO: - episode: 342, ep_reward: 63.81426093880466, ep_step: 1000 +2023-05-26 13:44:27 - SimpleLog - INFO: - episode: 343, ep_reward: 114.83240664140128, ep_step: 1000 +2023-05-26 13:44:29 - SimpleLog - INFO: - episode: 344, ep_reward: 148.09924626105217, ep_step: 1000 +2023-05-26 13:44:31 - SimpleLog - INFO: - episode: 345, ep_reward: 201.23841064359792, ep_step: 1000 +2023-05-26 13:44:32 - SimpleLog - INFO: - episode: 346, ep_reward: 247.19563198778144, ep_step: 1000 +2023-05-26 13:44:34 - SimpleLog - INFO: - episode: 347, ep_reward: 123.54693535268179, ep_step: 1000 +2023-05-26 13:44:36 - SimpleLog - INFO: - episode: 348, ep_reward: 34.075846829562614, ep_step: 1000 +2023-05-26 13:44:38 - SimpleLog - INFO: - episode: 349, ep_reward: 127.28519176335081, ep_step: 1000 +2023-05-26 13:44:40 - SimpleLog - INFO: - episode: 350, ep_reward: 85.62481390017498, ep_step: 1000 +2023-05-26 13:44:41 - SimpleLog - INFO: - episode: 351, ep_reward: 61.22587978733826, ep_step: 1000 +2023-05-26 13:44:43 - SimpleLog - INFO: - episode: 352, ep_reward: 136.56588467051327, ep_step: 1000 +2023-05-26 13:44:45 - SimpleLog - INFO: - episode: 353, ep_reward: 209.7067779897656, ep_step: 1000 +2023-05-26 13:44:46 - SimpleLog - INFO: - episode: 354, ep_reward: 74.82801730050022, ep_step: 1000 +2023-05-26 13:44:48 - SimpleLog - INFO: - episode: 355, ep_reward: 134.10631343749316, ep_step: 1000 +2023-05-26 13:44:50 - SimpleLog - INFO: - episode: 356, ep_reward: 107.47219956746218, ep_step: 1000 +2023-05-26 13:44:52 - SimpleLog - INFO: - episode: 357, ep_reward: 89.54227274842783, ep_step: 1000 +2023-05-26 13:44:54 - SimpleLog - INFO: - episode: 358, ep_reward: 109.85903216329773, ep_step: 1000 +2023-05-26 13:44:56 - SimpleLog - INFO: - episode: 359, ep_reward: 254.8134584359323, ep_step: 1000 +2023-05-26 13:44:58 - SimpleLog - INFO: - episode: 360, ep_reward: 140.17498495590405, ep_step: 1000 +2023-05-26 13:45:00 - SimpleLog - INFO: - episode: 361, ep_reward: 28.161293097613203, ep_step: 1000 +2023-05-26 13:45:01 - SimpleLog - INFO: - episode: 362, ep_reward: -39.9023326339731, ep_step: 1000 +2023-05-26 13:45:03 - SimpleLog - INFO: - episode: 363, ep_reward: 64.49995745530597, ep_step: 1000 +2023-05-26 13:45:05 - SimpleLog - INFO: - episode: 364, ep_reward: -130.6507241430073, ep_step: 1000 +2023-05-26 13:45:06 - SimpleLog - INFO: - episode: 365, ep_reward: 103.03003858985734, ep_step: 1000 +2023-05-26 13:45:08 - SimpleLog - INFO: - episode: 366, ep_reward: 229.73462310222936, ep_step: 1000 +2023-05-26 13:45:10 - SimpleLog - INFO: - episode: 367, ep_reward: 101.70610764058016, ep_step: 1000 +2023-05-26 13:45:11 - SimpleLog - INFO: - episode: 368, ep_reward: 64.1593597817845, ep_step: 1000 +2023-05-26 13:45:13 - SimpleLog - INFO: - episode: 369, ep_reward: 43.997668394352246, ep_step: 1000 +2023-05-26 13:45:15 - SimpleLog - INFO: - episode: 370, ep_reward: 177.676302168198, ep_step: 1000 +2023-05-26 13:45:16 - SimpleLog - INFO: - episode: 371, ep_reward: 192.8334824501915, ep_step: 1000 +2023-05-26 13:45:18 - SimpleLog - INFO: - episode: 372, ep_reward: 126.40808808528932, ep_step: 1000 +2023-05-26 13:45:20 - SimpleLog - INFO: - episode: 373, ep_reward: 137.08312223589428, ep_step: 1000 +2023-05-26 13:45:21 - SimpleLog - INFO: - episode: 374, ep_reward: 213.35225014432478, ep_step: 1000 +2023-05-26 13:45:23 - SimpleLog - INFO: - episode: 375, ep_reward: 253.45361459364526, ep_step: 1000 +2023-05-26 13:45:25 - SimpleLog - INFO: - episode: 376, ep_reward: 132.53410158813477, ep_step: 1000 +2023-05-26 13:45:27 - SimpleLog - INFO: - episode: 377, ep_reward: 225.36100598705858, ep_step: 1000 +2023-05-26 13:45:29 - SimpleLog - INFO: - episode: 378, ep_reward: 186.05344978689067, ep_step: 1000 +2023-05-26 13:45:30 - SimpleLog - INFO: - episode: 379, ep_reward: 93.42655532177284, ep_step: 1000 +2023-05-26 13:45:32 - SimpleLog - INFO: - episode: 380, ep_reward: 113.06786228813036, ep_step: 1000 +2023-05-26 13:45:34 - SimpleLog - INFO: - episode: 381, ep_reward: 158.66486775920342, ep_step: 1000 +2023-05-26 13:45:35 - SimpleLog - INFO: - episode: 382, ep_reward: 204.33946736594575, ep_step: 1000 +2023-05-26 13:45:42 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: 691.812 +2023-05-26 13:45:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 691.812, save the best model! +2023-05-26 13:45:42 - SimpleLog - INFO: - episode: 383, ep_reward: 196.65629593572038, ep_step: 1000 +2023-05-26 13:45:44 - SimpleLog - INFO: - episode: 384, ep_reward: 169.1446785994684, ep_step: 1000 +2023-05-26 13:45:45 - SimpleLog - INFO: - episode: 385, ep_reward: -3.8143925724005374, ep_step: 1000 +2023-05-26 13:45:46 - SimpleLog - INFO: - episode: 386, ep_reward: -60.941720328796805, ep_step: 1000 +2023-05-26 13:45:47 - SimpleLog - INFO: - episode: 387, ep_reward: 133.16405610438727, ep_step: 1000 +2023-05-26 13:45:49 - SimpleLog - INFO: - episode: 388, ep_reward: -73.98343794288216, ep_step: 1000 +2023-05-26 13:45:50 - SimpleLog - INFO: - episode: 389, ep_reward: 166.88827739744613, ep_step: 1000 +2023-05-26 13:45:51 - SimpleLog - INFO: - episode: 390, ep_reward: -113.55935786283924, ep_step: 1000 +2023-05-26 13:45:53 - SimpleLog - INFO: - episode: 391, ep_reward: 221.88168492787761, ep_step: 1000 +2023-05-26 13:45:54 - SimpleLog - INFO: - episode: 392, ep_reward: 69.70183356604095, ep_step: 1000 +2023-05-26 13:45:56 - SimpleLog - INFO: - episode: 393, ep_reward: -15.810067002437508, ep_step: 1000 +2023-05-26 13:45:58 - SimpleLog - INFO: - episode: 394, ep_reward: 183.65567996302957, ep_step: 1000 +2023-05-26 13:46:00 - SimpleLog - INFO: - episode: 395, ep_reward: 166.96955619810115, ep_step: 1000 +2023-05-26 13:46:02 - SimpleLog - INFO: - episode: 396, ep_reward: 64.52607292353389, ep_step: 1000 +2023-05-26 13:46:04 - SimpleLog - INFO: - episode: 397, ep_reward: 145.07860187050045, ep_step: 1000 +2023-05-26 13:46:06 - SimpleLog - INFO: - episode: 398, ep_reward: -208.15961764730125, ep_step: 1000 +2023-05-26 13:46:08 - SimpleLog - INFO: - episode: 399, ep_reward: 197.05258082043582, ep_step: 1000 +2023-05-26 13:46:09 - SimpleLog - INFO: - episode: 400, ep_reward: 16.340774376566877, ep_step: 1000 +2023-05-26 13:46:11 - SimpleLog - INFO: - episode: 401, ep_reward: -39.761652134908154, ep_step: 1000 +2023-05-26 13:46:13 - SimpleLog - INFO: - episode: 402, ep_reward: 273.6966105789013, ep_step: 1000 +2023-05-26 13:46:14 - SimpleLog - INFO: - episode: 403, ep_reward: 120.26118092901221, ep_step: 1000 +2023-05-26 13:46:16 - SimpleLog - INFO: - episode: 404, ep_reward: 188.37184760393436, ep_step: 1000 +2023-05-26 13:46:18 - SimpleLog - INFO: - episode: 405, ep_reward: 148.2098131802336, ep_step: 1000 +2023-05-26 13:46:20 - SimpleLog - INFO: - episode: 406, ep_reward: 122.64775468643307, ep_step: 1000 +2023-05-26 13:46:21 - SimpleLog - INFO: - episode: 407, ep_reward: -2.4309715171563457, ep_step: 1000 +2023-05-26 13:46:23 - SimpleLog - INFO: - episode: 408, ep_reward: 206.4892629552765, ep_step: 1000 +2023-05-26 13:46:25 - SimpleLog - INFO: - episode: 409, ep_reward: 30.650090201536948, ep_step: 1000 +2023-05-26 13:46:26 - SimpleLog - INFO: - episode: 410, ep_reward: 149.02358883633718, ep_step: 1000 +2023-05-26 13:46:28 - SimpleLog - INFO: - episode: 411, ep_reward: 260.2664039707724, ep_step: 1000 +2023-05-26 13:46:30 - SimpleLog - INFO: - episode: 412, ep_reward: 277.47624591483213, ep_step: 1000 +2023-05-26 13:46:32 - SimpleLog - INFO: - episode: 413, ep_reward: 176.03100076689432, ep_step: 1000 +2023-05-26 13:46:34 - SimpleLog - INFO: - episode: 414, ep_reward: 151.3236885837471, ep_step: 1000 +2023-05-26 13:46:35 - SimpleLog - INFO: - episode: 415, ep_reward: 175.235410614303, ep_step: 1000 +2023-05-26 13:46:37 - SimpleLog - INFO: - episode: 416, ep_reward: 6.633853647977023, ep_step: 1000 +2023-05-26 13:46:39 - SimpleLog - INFO: - episode: 417, ep_reward: -28.899888354238954, ep_step: 1000 +2023-05-26 13:46:41 - SimpleLog - INFO: - episode: 418, ep_reward: 258.5808609982163, ep_step: 1000 +2023-05-26 13:46:42 - SimpleLog - INFO: - episode: 419, ep_reward: 205.4221647615732, ep_step: 1000 +2023-05-26 13:46:44 - SimpleLog - INFO: - episode: 420, ep_reward: 232.74049075141107, ep_step: 1000 +2023-05-26 13:46:46 - SimpleLog - INFO: - episode: 421, ep_reward: 156.36594501669427, ep_step: 1000 +2023-05-26 13:46:48 - SimpleLog - INFO: - episode: 422, ep_reward: 125.15197624706464, ep_step: 1000 +2023-05-26 13:46:49 - SimpleLog - INFO: - episode: 423, ep_reward: -90.25026257656657, ep_step: 1000 +2023-05-26 13:46:51 - SimpleLog - INFO: - episode: 424, ep_reward: 125.91409199756681, ep_step: 1000 +2023-05-26 13:46:53 - SimpleLog - INFO: - episode: 425, ep_reward: 201.74568876335604, ep_step: 1000 +2023-05-26 13:46:54 - SimpleLog - INFO: - episode: 426, ep_reward: -144.60667530685566, ep_step: 1000 +2023-05-26 13:46:56 - SimpleLog - INFO: - episode: 427, ep_reward: -231.4061423145267, ep_step: 1000 +2023-05-26 13:46:58 - SimpleLog - INFO: - episode: 428, ep_reward: 129.20443774672142, ep_step: 1000 +2023-05-26 13:47:00 - SimpleLog - INFO: - episode: 429, ep_reward: 178.33155892970808, ep_step: 1000 +2023-05-26 13:47:01 - SimpleLog - INFO: - episode: 430, ep_reward: 73.00813522771408, ep_step: 1000 +2023-05-26 13:47:03 - SimpleLog - INFO: - episode: 431, ep_reward: 298.60104853461206, ep_step: 1000 +2023-05-26 13:47:06 - SimpleLog - INFO: - episode: 432, ep_reward: 307.9754852419405, ep_step: 1000 +2023-05-26 13:47:08 - SimpleLog - INFO: - episode: 433, ep_reward: 121.01724656483935, ep_step: 1000 +2023-05-26 13:47:10 - SimpleLog - INFO: - episode: 434, ep_reward: 251.42291977384292, ep_step: 1000 +2023-05-26 13:47:12 - SimpleLog - INFO: - episode: 435, ep_reward: -5.6615092157746005, ep_step: 1000 +2023-05-26 13:47:14 - SimpleLog - INFO: - episode: 436, ep_reward: 360.9673697254383, ep_step: 1000 +2023-05-26 13:47:15 - SimpleLog - INFO: - episode: 437, ep_reward: 378.19253416487203, ep_step: 1000 +2023-05-26 13:47:17 - SimpleLog - INFO: - episode: 438, ep_reward: 176.37358827601514, ep_step: 1000 +2023-05-26 13:47:18 - SimpleLog - INFO: - episode: 439, ep_reward: 249.83340472136666, ep_step: 1000 +2023-05-26 13:47:20 - SimpleLog - INFO: - episode: 440, ep_reward: 262.438785266595, ep_step: 1000 +2023-05-26 13:47:22 - SimpleLog - INFO: - episode: 441, ep_reward: 280.8457663558846, ep_step: 1000 +2023-05-26 13:47:24 - SimpleLog - INFO: - episode: 442, ep_reward: 337.8513082646748, ep_step: 1000 +2023-05-26 13:47:25 - SimpleLog - INFO: - episode: 443, ep_reward: 298.1054611484894, ep_step: 1000 +2023-05-26 13:47:27 - SimpleLog - INFO: - episode: 444, ep_reward: 269.49739590581504, ep_step: 1000 +2023-05-26 13:47:29 - SimpleLog - INFO: - episode: 445, ep_reward: 323.82146487958664, ep_step: 1000 +2023-05-26 13:47:31 - SimpleLog - INFO: - episode: 446, ep_reward: 127.33279568914213, ep_step: 1000 +2023-05-26 13:47:32 - SimpleLog - INFO: - episode: 447, ep_reward: 337.05945933292094, ep_step: 1000 +2023-05-26 13:47:34 - SimpleLog - INFO: - episode: 448, ep_reward: 330.9341636590493, ep_step: 1000 +2023-05-26 13:47:36 - SimpleLog - INFO: - episode: 449, ep_reward: 159.07699291352688, ep_step: 1000 +2023-05-26 13:47:37 - SimpleLog - INFO: - episode: 450, ep_reward: 322.45791539126066, ep_step: 1000 +2023-05-26 13:47:39 - SimpleLog - INFO: - episode: 451, ep_reward: 53.16967976686795, ep_step: 1000 +2023-05-26 13:47:41 - SimpleLog - INFO: - episode: 452, ep_reward: 311.47612960034235, ep_step: 1000 +2023-05-26 13:47:43 - SimpleLog - INFO: - episode: 453, ep_reward: 458.42182883087287, ep_step: 1000 +2023-05-26 13:47:45 - SimpleLog - INFO: - episode: 454, ep_reward: 156.8223265060659, ep_step: 1000 +2023-05-26 13:47:46 - SimpleLog - INFO: - episode: 455, ep_reward: 313.7690344329545, ep_step: 1000 +2023-05-26 13:47:48 - SimpleLog - INFO: - episode: 456, ep_reward: 211.26534914265963, ep_step: 1000 +2023-05-26 13:47:50 - SimpleLog - INFO: - episode: 457, ep_reward: 275.79124966014024, ep_step: 1000 +2023-05-26 13:47:51 - SimpleLog - INFO: - episode: 458, ep_reward: 240.73799402605255, ep_step: 1000 +2023-05-26 13:47:53 - SimpleLog - INFO: - episode: 459, ep_reward: 437.8169394033874, ep_step: 1000 +2023-05-26 13:47:55 - SimpleLog - INFO: - episode: 460, ep_reward: 316.3393550340899, ep_step: 1000 +2023-05-26 13:47:56 - SimpleLog - INFO: - episode: 461, ep_reward: 326.4948210563962, ep_step: 1000 +2023-05-26 13:47:58 - SimpleLog - INFO: - episode: 462, ep_reward: 263.03410700352947, ep_step: 1000 +2023-05-26 13:48:00 - SimpleLog - INFO: - episode: 463, ep_reward: 356.96466738933617, ep_step: 1000 +2023-05-26 13:48:02 - SimpleLog - INFO: - episode: 464, ep_reward: 639.6459301910734, ep_step: 1000 +2023-05-26 13:48:03 - SimpleLog - INFO: - episode: 465, ep_reward: 264.9769397671442, ep_step: 1000 +2023-05-26 13:48:05 - SimpleLog - INFO: - episode: 466, ep_reward: 280.9395976233423, ep_step: 1000 +2023-05-26 13:48:07 - SimpleLog - INFO: - episode: 467, ep_reward: 327.3512749257104, ep_step: 1000 +2023-05-26 13:48:08 - SimpleLog - INFO: - episode: 468, ep_reward: 265.40099878378425, ep_step: 1000 +2023-05-26 13:48:10 - SimpleLog - INFO: - episode: 469, ep_reward: 300.6346727658386, ep_step: 1000 +2023-05-26 13:48:13 - SimpleLog - INFO: - episode: 470, ep_reward: 481.829673553012, ep_step: 1000 +2023-05-26 13:48:15 - SimpleLog - INFO: - episode: 471, ep_reward: 340.45885165442235, ep_step: 1000 +2023-05-26 13:48:17 - SimpleLog - INFO: - episode: 472, ep_reward: 171.19119375921218, ep_step: 1000 +2023-05-26 13:48:18 - SimpleLog - INFO: - episode: 473, ep_reward: 285.3880095616515, ep_step: 1000 +2023-05-26 13:48:20 - SimpleLog - INFO: - episode: 474, ep_reward: 211.6333126642471, ep_step: 1000 +2023-05-26 13:48:22 - SimpleLog - INFO: - episode: 475, ep_reward: 376.3266064710855, ep_step: 1000 +2023-05-26 13:48:23 - SimpleLog - INFO: - episode: 476, ep_reward: 309.5839402616268, ep_step: 1000 +2023-05-26 13:48:25 - SimpleLog - INFO: - episode: 477, ep_reward: 273.264682040257, ep_step: 1000 +2023-05-26 13:48:27 - SimpleLog - INFO: - episode: 478, ep_reward: 333.33168004586173, ep_step: 1000 +2023-05-26 13:48:28 - SimpleLog - INFO: - episode: 479, ep_reward: 282.75387426727406, ep_step: 1000 +2023-05-26 13:48:30 - SimpleLog - INFO: - episode: 480, ep_reward: 320.094623996596, ep_step: 1000 +2023-05-26 13:48:32 - SimpleLog - INFO: - episode: 481, ep_reward: 321.82367458477006, ep_step: 1000 +2023-05-26 13:48:34 - SimpleLog - INFO: - episode: 482, ep_reward: 369.30163840180506, ep_step: 1000 +2023-05-26 13:48:35 - SimpleLog - INFO: - episode: 483, ep_reward: 289.3954657412336, ep_step: 1000 +2023-05-26 13:48:37 - SimpleLog - INFO: - episode: 484, ep_reward: 429.2415251487356, ep_step: 1000 +2023-05-26 13:48:39 - SimpleLog - INFO: - episode: 485, ep_reward: 254.3080506575478, ep_step: 1000 +2023-05-26 13:48:40 - SimpleLog - INFO: - episode: 486, ep_reward: 294.31303043853063, ep_step: 1000 +2023-05-26 13:48:42 - SimpleLog - INFO: - episode: 487, ep_reward: 155.28142361269275, ep_step: 1000 +2023-05-26 13:48:44 - SimpleLog - INFO: - episode: 488, ep_reward: 268.00317153395235, ep_step: 1000 +2023-05-26 13:48:46 - SimpleLog - INFO: - episode: 489, ep_reward: 378.60552336660885, ep_step: 1000 +2023-05-26 13:48:48 - SimpleLog - INFO: - episode: 490, ep_reward: 482.70841311807544, ep_step: 1000 +2023-05-26 13:48:49 - SimpleLog - INFO: - episode: 491, ep_reward: 295.1894728430266, ep_step: 1000 +2023-05-26 13:48:51 - SimpleLog - INFO: - episode: 492, ep_reward: 200.82988921949425, ep_step: 1000 +2023-05-26 13:48:53 - SimpleLog - INFO: - episode: 493, ep_reward: 325.2183766548131, ep_step: 1000 +2023-05-26 13:48:55 - SimpleLog - INFO: - episode: 494, ep_reward: -27.658203318848752, ep_step: 1000 +2023-05-26 13:48:56 - SimpleLog - INFO: - episode: 495, ep_reward: 405.5437830964723, ep_step: 1000 +2023-05-26 13:48:58 - SimpleLog - INFO: - episode: 496, ep_reward: 317.2457180345478, ep_step: 1000 +2023-05-26 13:49:00 - SimpleLog - INFO: - episode: 497, ep_reward: 267.619488608644, ep_step: 1000 +2023-05-26 13:49:01 - SimpleLog - INFO: - episode: 498, ep_reward: 456.45982340184065, ep_step: 1000 +2023-05-26 13:49:03 - SimpleLog - INFO: - episode: 499, ep_reward: 401.1402264208231, ep_step: 1000 +2023-05-26 13:49:05 - SimpleLog - INFO: - episode: 500, ep_reward: 486.0647493389166, ep_step: 1000 +2023-05-26 13:49:06 - SimpleLog - INFO: - episode: 501, ep_reward: 177.27570105381122, ep_step: 1000 +2023-05-26 13:49:08 - SimpleLog - INFO: - episode: 502, ep_reward: 221.50168801679342, ep_step: 1000 +2023-05-26 13:49:10 - SimpleLog - INFO: - episode: 503, ep_reward: 267.3676522856421, ep_step: 1000 +2023-05-26 13:49:12 - SimpleLog - INFO: - episode: 504, ep_reward: 373.24554366699334, ep_step: 1000 +2023-05-26 13:49:13 - SimpleLog - INFO: - episode: 505, ep_reward: 296.4765814616708, ep_step: 1000 +2023-05-26 13:49:15 - SimpleLog - INFO: - episode: 506, ep_reward: 411.94129743867643, ep_step: 1000 +2023-05-26 13:49:17 - SimpleLog - INFO: - episode: 507, ep_reward: 224.1293034463195, ep_step: 1000 +2023-05-26 13:49:19 - SimpleLog - INFO: - episode: 508, ep_reward: 301.9435170267188, ep_step: 1000 +2023-05-26 13:49:21 - SimpleLog - INFO: - episode: 509, ep_reward: 281.560192502429, ep_step: 1000 +2023-05-26 13:49:23 - SimpleLog - INFO: - episode: 510, ep_reward: 282.2585816449573, ep_step: 1000 +2023-05-26 13:49:30 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: -261.445 +2023-05-26 13:49:30 - SimpleLog - INFO: - episode: 511, ep_reward: 381.7858527305998, ep_step: 1000 +2023-05-26 13:49:31 - SimpleLog - INFO: - episode: 512, ep_reward: -0.6981961932187049, ep_step: 1000 +2023-05-26 13:49:32 - SimpleLog - INFO: - episode: 513, ep_reward: 297.31195769996356, ep_step: 1000 +2023-05-26 13:49:34 - SimpleLog - INFO: - episode: 514, ep_reward: 375.4013749584137, ep_step: 1000 +2023-05-26 13:49:35 - SimpleLog - INFO: - episode: 515, ep_reward: 308.97353766404956, ep_step: 1000 +2023-05-26 13:49:37 - SimpleLog - INFO: - episode: 516, ep_reward: 274.13716670943427, ep_step: 1000 +2023-05-26 13:49:38 - SimpleLog - INFO: - episode: 517, ep_reward: 400.34867987649113, ep_step: 1000 +2023-05-26 13:49:40 - SimpleLog - INFO: - episode: 518, ep_reward: 369.3075615094145, ep_step: 1000 +2023-05-26 13:49:41 - SimpleLog - INFO: - episode: 519, ep_reward: 258.2155111057153, ep_step: 1000 +2023-05-26 13:49:43 - SimpleLog - INFO: - episode: 520, ep_reward: 305.57693366103797, ep_step: 1000 +2023-05-26 13:49:45 - SimpleLog - INFO: - episode: 521, ep_reward: 431.70837978269043, ep_step: 1000 +2023-05-26 13:49:47 - SimpleLog - INFO: - episode: 522, ep_reward: 255.73808184927807, ep_step: 1000 +2023-05-26 13:49:48 - SimpleLog - INFO: - episode: 523, ep_reward: 387.8418021610095, ep_step: 1000 +2023-05-26 13:49:50 - SimpleLog - INFO: - episode: 524, ep_reward: 260.0371173978128, ep_step: 1000 +2023-05-26 13:49:52 - SimpleLog - INFO: - episode: 525, ep_reward: 454.86400782461146, ep_step: 1000 +2023-05-26 13:49:54 - SimpleLog - INFO: - episode: 526, ep_reward: 276.95686209114433, ep_step: 1000 +2023-05-26 13:49:56 - SimpleLog - INFO: - episode: 527, ep_reward: 287.18352982370806, ep_step: 1000 +2023-05-26 13:49:57 - SimpleLog - INFO: - episode: 528, ep_reward: 402.12155848652367, ep_step: 1000 +2023-05-26 13:49:59 - SimpleLog - INFO: - episode: 529, ep_reward: 403.63160922995576, ep_step: 1000 +2023-05-26 13:50:01 - SimpleLog - INFO: - episode: 530, ep_reward: 271.7881541261978, ep_step: 1000 +2023-05-26 13:50:02 - SimpleLog - INFO: - episode: 531, ep_reward: 380.2479912467473, ep_step: 1000 +2023-05-26 13:50:04 - SimpleLog - INFO: - episode: 532, ep_reward: 350.58978456748923, ep_step: 1000 +2023-05-26 13:50:06 - SimpleLog - INFO: - episode: 533, ep_reward: 316.93489372601596, ep_step: 1000 +2023-05-26 13:50:08 - SimpleLog - INFO: - episode: 534, ep_reward: 486.1096730948378, ep_step: 1000 +2023-05-26 13:50:10 - SimpleLog - INFO: - episode: 535, ep_reward: 397.71368176496594, ep_step: 1000 +2023-05-26 13:50:12 - SimpleLog - INFO: - episode: 536, ep_reward: 326.91149425404643, ep_step: 1000 +2023-05-26 13:50:13 - SimpleLog - INFO: - episode: 537, ep_reward: 442.44265020189334, ep_step: 1000 +2023-05-26 13:50:15 - SimpleLog - INFO: - episode: 538, ep_reward: 363.03886652546095, ep_step: 1000 +2023-05-26 13:50:17 - SimpleLog - INFO: - episode: 539, ep_reward: 186.17598856835627, ep_step: 1000 +2023-05-26 13:50:19 - SimpleLog - INFO: - episode: 540, ep_reward: 432.4851633494294, ep_step: 1000 +2023-05-26 13:50:20 - SimpleLog - INFO: - episode: 541, ep_reward: 248.35735591314358, ep_step: 1000 +2023-05-26 13:50:22 - SimpleLog - INFO: - episode: 542, ep_reward: -124.70420393287894, ep_step: 1000 +2023-05-26 13:50:24 - SimpleLog - INFO: - episode: 543, ep_reward: 283.0152349391718, ep_step: 1000 +2023-05-26 13:50:26 - SimpleLog - INFO: - episode: 544, ep_reward: 200.23882449552616, ep_step: 1000 +2023-05-26 13:50:28 - SimpleLog - INFO: - episode: 545, ep_reward: 298.01524653953817, ep_step: 1000 +2023-05-26 13:50:30 - SimpleLog - INFO: - episode: 546, ep_reward: 330.70794094071823, ep_step: 1000 +2023-05-26 13:50:31 - SimpleLog - INFO: - episode: 547, ep_reward: 273.61231603040864, ep_step: 1000 +2023-05-26 13:50:33 - SimpleLog - INFO: - episode: 548, ep_reward: 267.01093463939077, ep_step: 1000 +2023-05-26 13:50:35 - SimpleLog - INFO: - episode: 549, ep_reward: 391.30307847892396, ep_step: 1000 +2023-05-26 13:50:36 - SimpleLog - INFO: - episode: 550, ep_reward: 351.7260754807102, ep_step: 1000 +2023-05-26 13:50:38 - SimpleLog - INFO: - episode: 551, ep_reward: 468.4394855277351, ep_step: 1000 +2023-05-26 13:50:40 - SimpleLog - INFO: - episode: 552, ep_reward: 316.1243817452702, ep_step: 1000 +2023-05-26 13:50:41 - SimpleLog - INFO: - episode: 553, ep_reward: 293.07772944924614, ep_step: 1000 +2023-05-26 13:50:43 - SimpleLog - INFO: - episode: 554, ep_reward: 235.22299033798083, ep_step: 1000 +2023-05-26 13:50:45 - SimpleLog - INFO: - episode: 555, ep_reward: 291.8857359836165, ep_step: 1000 +2023-05-26 13:50:47 - SimpleLog - INFO: - episode: 556, ep_reward: 469.5887347076242, ep_step: 1000 +2023-05-26 13:50:48 - SimpleLog - INFO: - episode: 557, ep_reward: 16.974417940210174, ep_step: 1000 +2023-05-26 13:50:50 - SimpleLog - INFO: - episode: 558, ep_reward: 222.2183000714615, ep_step: 1000 +2023-05-26 13:50:52 - SimpleLog - INFO: - episode: 559, ep_reward: 382.12278030616295, ep_step: 1000 +2023-05-26 13:50:53 - SimpleLog - INFO: - episode: 560, ep_reward: 329.53982393090394, ep_step: 1000 +2023-05-26 13:50:55 - SimpleLog - INFO: - episode: 561, ep_reward: 279.5837697571215, ep_step: 1000 +2023-05-26 13:50:57 - SimpleLog - INFO: - episode: 562, ep_reward: 396.16536639838745, ep_step: 1000 +2023-05-26 13:50:58 - SimpleLog - INFO: - episode: 563, ep_reward: 317.20142034317047, ep_step: 1000 +2023-05-26 13:51:00 - SimpleLog - INFO: - episode: 564, ep_reward: 517.2473021837459, ep_step: 1000 +2023-05-26 13:51:02 - SimpleLog - INFO: - episode: 565, ep_reward: 235.92640818033942, ep_step: 1000 +2023-05-26 13:51:03 - SimpleLog - INFO: - episode: 566, ep_reward: 201.78186161342722, ep_step: 1000 +2023-05-26 13:51:05 - SimpleLog - INFO: - episode: 567, ep_reward: 183.86135142112076, ep_step: 1000 +2023-05-26 13:51:07 - SimpleLog - INFO: - episode: 568, ep_reward: 186.65857548182098, ep_step: 1000 +2023-05-26 13:51:08 - SimpleLog - INFO: - episode: 569, ep_reward: 572.5357462300901, ep_step: 1000 +2023-05-26 13:51:10 - SimpleLog - INFO: - episode: 570, ep_reward: 379.838929678009, ep_step: 1000 +2023-05-26 13:51:12 - SimpleLog - INFO: - episode: 571, ep_reward: 439.80534968765653, ep_step: 1000 +2023-05-26 13:51:13 - SimpleLog - INFO: - episode: 572, ep_reward: 356.0184175863256, ep_step: 1000 +2023-05-26 13:51:15 - SimpleLog - INFO: - episode: 573, ep_reward: 122.08357841368716, ep_step: 1000 +2023-05-26 13:51:17 - SimpleLog - INFO: - episode: 574, ep_reward: 148.94216532265938, ep_step: 1000 +2023-05-26 13:51:18 - SimpleLog - INFO: - episode: 575, ep_reward: 333.7519148468228, ep_step: 1000 +2023-05-26 13:51:20 - SimpleLog - INFO: - episode: 576, ep_reward: 211.11741901365215, ep_step: 1000 +2023-05-26 13:51:22 - SimpleLog - INFO: - episode: 577, ep_reward: 101.62376069239538, ep_step: 1000 +2023-05-26 13:51:23 - SimpleLog - INFO: - episode: 578, ep_reward: 454.2343650496696, ep_step: 1000 +2023-05-26 13:51:25 - SimpleLog - INFO: - episode: 579, ep_reward: -95.55132341459876, ep_step: 1000 +2023-05-26 13:51:27 - SimpleLog - INFO: - episode: 580, ep_reward: 326.0088126408997, ep_step: 1000 +2023-05-26 13:51:29 - SimpleLog - INFO: - episode: 581, ep_reward: 354.4948043515666, ep_step: 1000 +2023-05-26 13:51:31 - SimpleLog - INFO: - episode: 582, ep_reward: 213.02006512553461, ep_step: 1000 +2023-05-26 13:51:33 - SimpleLog - INFO: - episode: 583, ep_reward: 304.9460410850283, ep_step: 1000 +2023-05-26 13:51:35 - SimpleLog - INFO: - episode: 584, ep_reward: 382.2336973073948, ep_step: 1000 +2023-05-26 13:51:37 - SimpleLog - INFO: - episode: 585, ep_reward: 139.5106850110518, ep_step: 1000 +2023-05-26 13:51:39 - SimpleLog - INFO: - episode: 586, ep_reward: 293.84933344675034, ep_step: 1000 +2023-05-26 13:51:40 - SimpleLog - INFO: - episode: 587, ep_reward: 219.18215404389926, ep_step: 1000 +2023-05-26 13:51:42 - SimpleLog - INFO: - episode: 588, ep_reward: 327.6641247827755, ep_step: 1000 +2023-05-26 13:51:44 - SimpleLog - INFO: - episode: 589, ep_reward: 152.8869700194315, ep_step: 1000 +2023-05-26 13:51:46 - SimpleLog - INFO: - episode: 590, ep_reward: -34.791690463823, ep_step: 1000 +2023-05-26 13:51:48 - SimpleLog - INFO: - episode: 591, ep_reward: 264.8767560321309, ep_step: 1000 +2023-05-26 13:51:49 - SimpleLog - INFO: - episode: 592, ep_reward: 338.80640537927184, ep_step: 1000 +2023-05-26 13:51:51 - SimpleLog - INFO: - episode: 593, ep_reward: 154.55664897718782, ep_step: 1000 +2023-05-26 13:51:53 - SimpleLog - INFO: - episode: 594, ep_reward: 129.63737791527015, ep_step: 1000 +2023-05-26 13:51:55 - SimpleLog - INFO: - episode: 595, ep_reward: 254.63273443102892, ep_step: 1000 +2023-05-26 13:51:56 - SimpleLog - INFO: - episode: 596, ep_reward: 287.96465843538476, ep_step: 1000 +2023-05-26 13:51:58 - SimpleLog - INFO: - episode: 597, ep_reward: -42.22551783305357, ep_step: 1000 +2023-05-26 13:52:00 - SimpleLog - INFO: - episode: 598, ep_reward: 495.43120568113375, ep_step: 1000 +2023-05-26 13:52:01 - SimpleLog - INFO: - episode: 599, ep_reward: 252.52569809812786, ep_step: 1000 +2023-05-26 13:52:03 - SimpleLog - INFO: - episode: 600, ep_reward: 279.9593527218097, ep_step: 1000 +2023-05-26 13:52:05 - SimpleLog - INFO: - episode: 601, ep_reward: 318.6808546413431, ep_step: 1000 +2023-05-26 13:52:07 - SimpleLog - INFO: - episode: 602, ep_reward: 314.6136463334472, ep_step: 1000 +2023-05-26 13:52:08 - SimpleLog - INFO: - episode: 603, ep_reward: 342.9627041303012, ep_step: 1000 +2023-05-26 13:52:10 - SimpleLog - INFO: - episode: 604, ep_reward: 324.6935366696987, ep_step: 1000 +2023-05-26 13:52:12 - SimpleLog - INFO: - episode: 605, ep_reward: 269.59758377963857, ep_step: 1000 +2023-05-26 13:52:13 - SimpleLog - INFO: - episode: 606, ep_reward: 391.106712305682, ep_step: 1000 +2023-05-26 13:52:15 - SimpleLog - INFO: - episode: 607, ep_reward: 316.00146715460716, ep_step: 1000 +2023-05-26 13:52:16 - SimpleLog - INFO: - episode: 608, ep_reward: 306.44736362257555, ep_step: 1000 +2023-05-26 13:52:18 - SimpleLog - INFO: - episode: 609, ep_reward: 421.0091155281624, ep_step: 1000 +2023-05-26 13:52:20 - SimpleLog - INFO: - episode: 610, ep_reward: 414.36617962791394, ep_step: 1000 +2023-05-26 13:52:21 - SimpleLog - INFO: - episode: 611, ep_reward: 323.1639216631517, ep_step: 1000 +2023-05-26 13:52:23 - SimpleLog - INFO: - episode: 612, ep_reward: 245.42861599046628, ep_step: 1000 +2023-05-26 13:52:25 - SimpleLog - INFO: - episode: 613, ep_reward: 332.22156032448703, ep_step: 1000 +2023-05-26 13:52:26 - SimpleLog - INFO: - episode: 614, ep_reward: 258.1834163212117, ep_step: 1000 +2023-05-26 13:52:28 - SimpleLog - INFO: - episode: 615, ep_reward: 318.9579734726453, ep_step: 1000 +2023-05-26 13:52:30 - SimpleLog - INFO: - episode: 616, ep_reward: 188.59939342626225, ep_step: 1000 +2023-05-26 13:52:31 - SimpleLog - INFO: - episode: 617, ep_reward: 405.9748453926245, ep_step: 1000 +2023-05-26 13:52:33 - SimpleLog - INFO: - episode: 618, ep_reward: 483.0915618279747, ep_step: 1000 +2023-05-26 13:52:35 - SimpleLog - INFO: - episode: 619, ep_reward: 541.3456779552564, ep_step: 1000 +2023-05-26 13:52:37 - SimpleLog - INFO: - episode: 620, ep_reward: 378.9339923551028, ep_step: 1000 +2023-05-26 13:52:39 - SimpleLog - INFO: - episode: 621, ep_reward: 398.60451248923556, ep_step: 1000 +2023-05-26 13:52:41 - SimpleLog - INFO: - episode: 622, ep_reward: 197.82769629180729, ep_step: 1000 +2023-05-26 13:52:43 - SimpleLog - INFO: - episode: 623, ep_reward: 323.81719301225723, ep_step: 1000 +2023-05-26 13:52:45 - SimpleLog - INFO: - episode: 624, ep_reward: 268.6736465441873, ep_step: 1000 +2023-05-26 13:52:47 - SimpleLog - INFO: - episode: 625, ep_reward: 466.48375304353846, ep_step: 1000 +2023-05-26 13:52:49 - SimpleLog - INFO: - episode: 626, ep_reward: 314.06544851325174, ep_step: 1000 +2023-05-26 13:52:50 - SimpleLog - INFO: - episode: 627, ep_reward: 305.97953471092035, ep_step: 1000 +2023-05-26 13:52:52 - SimpleLog - INFO: - episode: 628, ep_reward: 463.47946039321494, ep_step: 1000 +2023-05-26 13:52:53 - SimpleLog - INFO: - episode: 629, ep_reward: 321.4969787514513, ep_step: 1000 +2023-05-26 13:52:55 - SimpleLog - INFO: - episode: 630, ep_reward: 370.48207001805577, ep_step: 1000 +2023-05-26 13:52:57 - SimpleLog - INFO: - episode: 631, ep_reward: 456.4906072204532, ep_step: 1000 +2023-05-26 13:52:59 - SimpleLog - INFO: - episode: 632, ep_reward: 398.214149352944, ep_step: 1000 +2023-05-26 13:53:00 - SimpleLog - INFO: - episode: 633, ep_reward: 438.25394373116376, ep_step: 1000 +2023-05-26 13:53:02 - SimpleLog - INFO: - episode: 634, ep_reward: 448.33474227306993, ep_step: 1000 +2023-05-26 13:53:03 - SimpleLog - INFO: - episode: 635, ep_reward: 507.130221780664, ep_step: 1000 +2023-05-26 13:53:05 - SimpleLog - INFO: - episode: 636, ep_reward: 515.8777058569951, ep_step: 1000 +2023-05-26 13:53:07 - SimpleLog - INFO: - episode: 637, ep_reward: 727.2265965650746, ep_step: 1000 +2023-05-26 13:53:09 - SimpleLog - INFO: - episode: 638, ep_reward: 445.63348191567087, ep_step: 1000 +2023-05-26 13:53:15 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: 670.869 +2023-05-26 13:53:15 - SimpleLog - INFO: - episode: 639, ep_reward: 312.2684176152868, ep_step: 1000 +2023-05-26 13:53:17 - SimpleLog - INFO: - episode: 640, ep_reward: 343.9018508021401, ep_step: 1000 +2023-05-26 13:53:18 - SimpleLog - INFO: - episode: 641, ep_reward: 374.94239737904866, ep_step: 1000 +2023-05-26 13:53:19 - SimpleLog - INFO: - episode: 642, ep_reward: 134.16344155414097, ep_step: 1000 +2023-05-26 13:53:20 - SimpleLog - INFO: - episode: 643, ep_reward: 112.58476771045895, ep_step: 1000 +2023-05-26 13:53:22 - SimpleLog - INFO: - episode: 644, ep_reward: 335.96046741151724, ep_step: 1000 +2023-05-26 13:53:23 - SimpleLog - INFO: - episode: 645, ep_reward: 440.14861091000046, ep_step: 1000 +2023-05-26 13:53:24 - SimpleLog - INFO: - episode: 646, ep_reward: 461.2283205021421, ep_step: 1000 +2023-05-26 13:53:25 - SimpleLog - INFO: - episode: 647, ep_reward: 263.0485821844548, ep_step: 1000 +2023-05-26 13:53:27 - SimpleLog - INFO: - episode: 648, ep_reward: 243.46116036978998, ep_step: 1000 +2023-05-26 13:53:28 - SimpleLog - INFO: - episode: 649, ep_reward: 431.77160805420215, ep_step: 1000 +2023-05-26 13:53:29 - SimpleLog - INFO: - episode: 650, ep_reward: 403.1687932703822, ep_step: 1000 +2023-05-26 13:53:30 - SimpleLog - INFO: - episode: 651, ep_reward: 610.9022278749012, ep_step: 1000 +2023-05-26 13:53:32 - SimpleLog - INFO: - episode: 652, ep_reward: 760.3798679388518, ep_step: 1000 +2023-05-26 13:53:33 - SimpleLog - INFO: - episode: 653, ep_reward: 422.40710636777146, ep_step: 1000 +2023-05-26 13:53:34 - SimpleLog - INFO: - episode: 654, ep_reward: 102.22355106152963, ep_step: 1000 +2023-05-26 13:53:35 - SimpleLog - INFO: - episode: 655, ep_reward: 429.12458948669644, ep_step: 1000 +2023-05-26 13:53:37 - SimpleLog - INFO: - episode: 656, ep_reward: 421.842459384628, ep_step: 1000 +2023-05-26 13:53:38 - SimpleLog - INFO: - episode: 657, ep_reward: 316.66236401187814, ep_step: 1000 +2023-05-26 13:53:39 - SimpleLog - INFO: - episode: 658, ep_reward: 627.0777923875179, ep_step: 1000 +2023-05-26 13:53:41 - SimpleLog - INFO: - episode: 659, ep_reward: 427.25355827615493, ep_step: 1000 +2023-05-26 13:53:43 - SimpleLog - INFO: - episode: 660, ep_reward: 185.95986646074894, ep_step: 1000 +2023-05-26 13:53:45 - SimpleLog - INFO: - episode: 661, ep_reward: 532.7841627322347, ep_step: 1000 +2023-05-26 13:53:47 - SimpleLog - INFO: - episode: 662, ep_reward: 676.8890702524657, ep_step: 1000 +2023-05-26 13:53:49 - SimpleLog - INFO: - episode: 663, ep_reward: 544.7237200488025, ep_step: 1000 +2023-05-26 13:53:51 - SimpleLog - INFO: - episode: 664, ep_reward: 360.5794159633059, ep_step: 1000 +2023-05-26 13:53:53 - SimpleLog - INFO: - episode: 665, ep_reward: 527.6547823856829, ep_step: 1000 +2023-05-26 13:53:54 - SimpleLog - INFO: - episode: 666, ep_reward: 465.68863366060964, ep_step: 1000 +2023-05-26 13:53:56 - SimpleLog - INFO: - episode: 667, ep_reward: 422.6288924242972, ep_step: 1000 +2023-05-26 13:53:58 - SimpleLog - INFO: - episode: 668, ep_reward: 497.4169842499802, ep_step: 1000 +2023-05-26 13:54:00 - SimpleLog - INFO: - episode: 669, ep_reward: 825.7787251990785, ep_step: 1000 +2023-05-26 13:54:01 - SimpleLog - INFO: - episode: 670, ep_reward: 585.748330676989, ep_step: 1000 +2023-05-26 13:54:03 - SimpleLog - INFO: - episode: 671, ep_reward: 416.9932760229128, ep_step: 1000 +2023-05-26 13:54:05 - SimpleLog - INFO: - episode: 672, ep_reward: 375.78745683016336, ep_step: 1000 +2023-05-26 13:54:06 - SimpleLog - INFO: - episode: 673, ep_reward: 421.6479689140658, ep_step: 1000 +2023-05-26 13:54:08 - SimpleLog - INFO: - episode: 674, ep_reward: 352.31583505823386, ep_step: 1000 +2023-05-26 13:54:10 - SimpleLog - INFO: - episode: 675, ep_reward: 473.4222660609877, ep_step: 1000 +2023-05-26 13:54:12 - SimpleLog - INFO: - episode: 676, ep_reward: 290.7658805979146, ep_step: 1000 +2023-05-26 13:54:13 - SimpleLog - INFO: - episode: 677, ep_reward: 392.0723577379376, ep_step: 1000 +2023-05-26 13:54:15 - SimpleLog - INFO: - episode: 678, ep_reward: 466.1942093735788, ep_step: 1000 +2023-05-26 13:54:17 - SimpleLog - INFO: - episode: 679, ep_reward: 353.07515130818877, ep_step: 1000 +2023-05-26 13:54:19 - SimpleLog - INFO: - episode: 680, ep_reward: 457.84420653325736, ep_step: 1000 +2023-05-26 13:54:20 - SimpleLog - INFO: - episode: 681, ep_reward: 286.8015327801055, ep_step: 1000 +2023-05-26 13:54:22 - SimpleLog - INFO: - episode: 682, ep_reward: 468.25635565551903, ep_step: 1000 +2023-05-26 13:54:23 - SimpleLog - INFO: - episode: 683, ep_reward: 467.24153579234036, ep_step: 1000 +2023-05-26 13:54:25 - SimpleLog - INFO: - episode: 684, ep_reward: 585.82697582763, ep_step: 1000 +2023-05-26 13:54:27 - SimpleLog - INFO: - episode: 685, ep_reward: 297.33945323936564, ep_step: 1000 +2023-05-26 13:54:28 - SimpleLog - INFO: - episode: 686, ep_reward: 553.7055201667235, ep_step: 1000 +2023-05-26 13:54:30 - SimpleLog - INFO: - episode: 687, ep_reward: 549.1967458707244, ep_step: 1000 +2023-05-26 13:54:32 - SimpleLog - INFO: - episode: 688, ep_reward: 425.5931278548404, ep_step: 1000 +2023-05-26 13:54:33 - SimpleLog - INFO: - episode: 689, ep_reward: 517.2964765265046, ep_step: 1000 +2023-05-26 13:54:35 - SimpleLog - INFO: - episode: 690, ep_reward: 523.3682525230811, ep_step: 1000 +2023-05-26 13:54:37 - SimpleLog - INFO: - episode: 691, ep_reward: 413.64480300590196, ep_step: 1000 +2023-05-26 13:54:38 - SimpleLog - INFO: - episode: 692, ep_reward: 730.1900820251115, ep_step: 1000 +2023-05-26 13:54:40 - SimpleLog - INFO: - episode: 693, ep_reward: 271.8651597675064, ep_step: 1000 +2023-05-26 13:54:42 - SimpleLog - INFO: - episode: 694, ep_reward: 527.4826082567729, ep_step: 1000 +2023-05-26 13:54:43 - SimpleLog - INFO: - episode: 695, ep_reward: 372.1109460371308, ep_step: 1000 +2023-05-26 13:54:45 - SimpleLog - INFO: - episode: 696, ep_reward: 497.6388271758559, ep_step: 1000 +2023-05-26 13:54:47 - SimpleLog - INFO: - episode: 697, ep_reward: 428.3847052268741, ep_step: 1000 +2023-05-26 13:54:48 - SimpleLog - INFO: - episode: 698, ep_reward: 342.5072456812043, ep_step: 1000 +2023-05-26 13:54:51 - SimpleLog - INFO: - episode: 699, ep_reward: 429.10860881207617, ep_step: 1000 +2023-05-26 13:54:52 - SimpleLog - INFO: - episode: 700, ep_reward: 459.519857982345, ep_step: 1000 +2023-05-26 13:54:55 - SimpleLog - INFO: - episode: 701, ep_reward: 446.46622057649597, ep_step: 1000 +2023-05-26 13:54:57 - SimpleLog - INFO: - episode: 702, ep_reward: 418.364359589943, ep_step: 1000 +2023-05-26 13:54:58 - SimpleLog - INFO: - episode: 703, ep_reward: 224.67127512381956, ep_step: 1000 +2023-05-26 13:55:00 - SimpleLog - INFO: - episode: 704, ep_reward: 477.8321113417666, ep_step: 1000 +2023-05-26 13:55:02 - SimpleLog - INFO: - episode: 705, ep_reward: 323.45309819838656, ep_step: 1000 +2023-05-26 13:55:03 - SimpleLog - INFO: - episode: 706, ep_reward: 300.55176660334826, ep_step: 1000 +2023-05-26 13:55:05 - SimpleLog - INFO: - episode: 707, ep_reward: 442.0627016267486, ep_step: 1000 +2023-05-26 13:55:07 - SimpleLog - INFO: - episode: 708, ep_reward: 717.2811239837977, ep_step: 1000 +2023-05-26 13:55:08 - SimpleLog - INFO: - episode: 709, ep_reward: 427.33176016832164, ep_step: 1000 +2023-05-26 13:55:10 - SimpleLog - INFO: - episode: 710, ep_reward: 584.8367759550838, ep_step: 1000 +2023-05-26 13:55:12 - SimpleLog - INFO: - episode: 711, ep_reward: 426.0051468229396, ep_step: 1000 +2023-05-26 13:55:13 - SimpleLog - INFO: - episode: 712, ep_reward: -265.6295531730259, ep_step: 1000 +2023-05-26 13:55:15 - SimpleLog - INFO: - episode: 713, ep_reward: 468.12129369543703, ep_step: 1000 +2023-05-26 13:55:17 - SimpleLog - INFO: - episode: 714, ep_reward: 399.4076883067623, ep_step: 1000 +2023-05-26 13:55:19 - SimpleLog - INFO: - episode: 715, ep_reward: 368.48948875694003, ep_step: 1000 +2023-05-26 13:55:20 - SimpleLog - INFO: - episode: 716, ep_reward: 588.3079479578507, ep_step: 1000 +2023-05-26 13:55:22 - SimpleLog - INFO: - episode: 717, ep_reward: 483.58719973073187, ep_step: 1000 +2023-05-26 13:55:24 - SimpleLog - INFO: - episode: 718, ep_reward: 408.16138512844697, ep_step: 1000 +2023-05-26 13:55:25 - SimpleLog - INFO: - episode: 719, ep_reward: 527.3602615739918, ep_step: 1000 +2023-05-26 13:55:27 - SimpleLog - INFO: - episode: 720, ep_reward: 302.35903707267545, ep_step: 1000 +2023-05-26 13:55:29 - SimpleLog - INFO: - episode: 721, ep_reward: 603.1089267101485, ep_step: 1000 +2023-05-26 13:55:30 - SimpleLog - INFO: - episode: 722, ep_reward: 111.15287014896985, ep_step: 1000 +2023-05-26 13:55:32 - SimpleLog - INFO: - episode: 723, ep_reward: 241.73428619327402, ep_step: 1000 +2023-05-26 13:55:34 - SimpleLog - INFO: - episode: 724, ep_reward: 443.34862790770404, ep_step: 1000 +2023-05-26 13:55:36 - SimpleLog - INFO: - episode: 725, ep_reward: 231.33493056841104, ep_step: 1000 +2023-05-26 13:55:37 - SimpleLog - INFO: - episode: 726, ep_reward: 237.6792318449926, ep_step: 1000 +2023-05-26 13:55:40 - SimpleLog - INFO: - episode: 727, ep_reward: 478.2242528630611, ep_step: 1000 +2023-05-26 13:55:42 - SimpleLog - INFO: - episode: 728, ep_reward: 464.0452674384979, ep_step: 1000 +2023-05-26 13:55:44 - SimpleLog - INFO: - episode: 729, ep_reward: 170.96070940815946, ep_step: 1000 +2023-05-26 13:55:47 - SimpleLog - INFO: - episode: 730, ep_reward: 291.1793439941036, ep_step: 1000 +2023-05-26 13:55:50 - SimpleLog - INFO: - episode: 731, ep_reward: 437.3727468652178, ep_step: 1000 +2023-05-26 13:55:52 - SimpleLog - INFO: - episode: 732, ep_reward: 446.94618357322366, ep_step: 1000 +2023-05-26 13:55:54 - SimpleLog - INFO: - episode: 733, ep_reward: 188.87385804184566, ep_step: 1000 +2023-05-26 13:55:56 - SimpleLog - INFO: - episode: 734, ep_reward: 324.55866448393436, ep_step: 1000 +2023-05-26 13:55:57 - SimpleLog - INFO: - episode: 735, ep_reward: 331.8044161044785, ep_step: 1000 +2023-05-26 13:55:59 - SimpleLog - INFO: - episode: 736, ep_reward: 293.659113400613, ep_step: 1000 +2023-05-26 13:56:01 - SimpleLog - INFO: - episode: 737, ep_reward: -84.46501936071681, ep_step: 1000 +2023-05-26 13:56:03 - SimpleLog - INFO: - episode: 738, ep_reward: 343.0356506949719, ep_step: 1000 +2023-05-26 13:56:04 - SimpleLog - INFO: - episode: 739, ep_reward: 483.4459686348101, ep_step: 1000 +2023-05-26 13:56:06 - SimpleLog - INFO: - episode: 740, ep_reward: 430.83105193961813, ep_step: 1000 +2023-05-26 13:56:08 - SimpleLog - INFO: - episode: 741, ep_reward: 397.30211291647254, ep_step: 1000 +2023-05-26 13:56:10 - SimpleLog - INFO: - episode: 742, ep_reward: 546.9773765613091, ep_step: 1000 +2023-05-26 13:56:11 - SimpleLog - INFO: - episode: 743, ep_reward: 99.22953555619554, ep_step: 1000 +2023-05-26 13:56:13 - SimpleLog - INFO: - episode: 744, ep_reward: 452.51514004418783, ep_step: 1000 +2023-05-26 13:56:15 - SimpleLog - INFO: - episode: 745, ep_reward: 364.3298692474322, ep_step: 1000 +2023-05-26 13:56:16 - SimpleLog - INFO: - episode: 746, ep_reward: 485.2514746474883, ep_step: 1000 +2023-05-26 13:56:18 - SimpleLog - INFO: - episode: 747, ep_reward: 354.94058678351325, ep_step: 1000 +2023-05-26 13:56:20 - SimpleLog - INFO: - episode: 748, ep_reward: 368.9470448831466, ep_step: 1000 +2023-05-26 13:56:22 - SimpleLog - INFO: - episode: 749, ep_reward: 528.8387468331586, ep_step: 1000 +2023-05-26 13:56:23 - SimpleLog - INFO: - episode: 750, ep_reward: 295.4933717000515, ep_step: 1000 +2023-05-26 13:56:25 - SimpleLog - INFO: - episode: 751, ep_reward: 397.45895675683096, ep_step: 1000 +2023-05-26 13:56:26 - SimpleLog - INFO: - episode: 752, ep_reward: 472.3680436806484, ep_step: 1000 +2023-05-26 13:56:28 - SimpleLog - INFO: - episode: 753, ep_reward: 524.262972648341, ep_step: 1000 +2023-05-26 13:56:30 - SimpleLog - INFO: - episode: 754, ep_reward: -71.92252464992393, ep_step: 1000 +2023-05-26 13:56:32 - SimpleLog - INFO: - episode: 755, ep_reward: 266.842663918606, ep_step: 1000 +2023-05-26 13:56:33 - SimpleLog - INFO: - episode: 756, ep_reward: 335.5099335630843, ep_step: 1000 +2023-05-26 13:56:35 - SimpleLog - INFO: - episode: 757, ep_reward: 465.9110054546448, ep_step: 1000 +2023-05-26 13:56:38 - SimpleLog - INFO: - episode: 758, ep_reward: 368.48235540336617, ep_step: 1000 +2023-05-26 13:56:40 - SimpleLog - INFO: - episode: 759, ep_reward: -25.99760860130958, ep_step: 1000 +2023-05-26 13:56:43 - SimpleLog - INFO: - episode: 760, ep_reward: 128.42628400817688, ep_step: 1000 +2023-05-26 13:56:45 - SimpleLog - INFO: - episode: 761, ep_reward: 364.41035870394455, ep_step: 1000 +2023-05-26 13:56:47 - SimpleLog - INFO: - episode: 762, ep_reward: 414.87423835914814, ep_step: 1000 +2023-05-26 13:56:50 - SimpleLog - INFO: - episode: 763, ep_reward: 112.23100370693481, ep_step: 1000 +2023-05-26 13:56:52 - SimpleLog - INFO: - episode: 764, ep_reward: 361.3345820784274, ep_step: 1000 +2023-05-26 13:56:55 - SimpleLog - INFO: - episode: 765, ep_reward: 419.7511252522276, ep_step: 1000 +2023-05-26 13:56:58 - SimpleLog - INFO: - episode: 766, ep_reward: 22.433030432106307, ep_step: 1000 +2023-05-26 13:57:07 - SimpleLog - INFO: - update_step: 3000, online_eval_reward: 900.989 +2023-05-26 13:57:07 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 900.989, save the best model! +2023-05-26 13:57:07 - SimpleLog - INFO: - episode: 767, ep_reward: 303.0353349107162, ep_step: 1000 +2023-05-26 13:57:09 - SimpleLog - INFO: - episode: 768, ep_reward: 367.41397773133656, ep_step: 1000 +2023-05-26 13:57:11 - SimpleLog - INFO: - episode: 769, ep_reward: 672.7070070914959, ep_step: 1000 +2023-05-26 13:57:13 - SimpleLog - INFO: - episode: 770, ep_reward: 264.0454253374896, ep_step: 1000 +2023-05-26 13:57:16 - SimpleLog - INFO: - episode: 771, ep_reward: 398.8970993444232, ep_step: 1000 +2023-05-26 13:57:18 - SimpleLog - INFO: - episode: 772, ep_reward: 204.3826002039711, ep_step: 1000 +2023-05-26 13:57:20 - SimpleLog - INFO: - episode: 773, ep_reward: 256.5973858977672, ep_step: 1000 +2023-05-26 13:57:23 - SimpleLog - INFO: - episode: 774, ep_reward: 407.13645870304293, ep_step: 1000 +2023-05-26 13:57:25 - SimpleLog - INFO: - episode: 775, ep_reward: 510.7890249767629, ep_step: 1000 +2023-05-26 13:57:28 - SimpleLog - INFO: - episode: 776, ep_reward: 328.40882300641385, ep_step: 1000 +2023-05-26 13:57:30 - SimpleLog - INFO: - episode: 777, ep_reward: 391.3889893934663, ep_step: 1000 +2023-05-26 13:57:32 - SimpleLog - INFO: - episode: 778, ep_reward: 454.42946608861286, ep_step: 1000 +2023-05-26 13:57:35 - SimpleLog - INFO: - episode: 779, ep_reward: 390.1323731987734, ep_step: 1000 +2023-05-26 13:57:37 - SimpleLog - INFO: - episode: 780, ep_reward: 416.64055722068707, ep_step: 1000 +2023-05-26 13:57:39 - SimpleLog - INFO: - episode: 781, ep_reward: 306.45011320121085, ep_step: 1000 +2023-05-26 13:57:42 - SimpleLog - INFO: - episode: 782, ep_reward: 389.3026207136965, ep_step: 1000 +2023-05-26 13:57:44 - SimpleLog - INFO: - episode: 783, ep_reward: 419.20886082083786, ep_step: 1000 +2023-05-26 13:57:47 - SimpleLog - INFO: - episode: 784, ep_reward: 536.3945387386669, ep_step: 1000 +2023-05-26 13:57:49 - SimpleLog - INFO: - episode: 785, ep_reward: 361.5848076787466, ep_step: 1000 +2023-05-26 13:57:52 - SimpleLog - INFO: - episode: 786, ep_reward: 388.6758294950114, ep_step: 1000 +2023-05-26 13:57:54 - SimpleLog - INFO: - episode: 787, ep_reward: 724.6199448931225, ep_step: 1000 +2023-05-26 13:57:56 - SimpleLog - INFO: - episode: 788, ep_reward: 500.27323017858623, ep_step: 1000 +2023-05-26 13:57:59 - SimpleLog - INFO: - episode: 789, ep_reward: 269.9056587542164, ep_step: 1000 +2023-05-26 13:58:01 - SimpleLog - INFO: - episode: 790, ep_reward: 187.18561775699231, ep_step: 1000 +2023-05-26 13:58:04 - SimpleLog - INFO: - episode: 791, ep_reward: 426.4946897546933, ep_step: 1000 +2023-05-26 13:58:06 - SimpleLog - INFO: - episode: 792, ep_reward: 268.90152704263903, ep_step: 1000 +2023-05-26 13:58:09 - SimpleLog - INFO: - episode: 793, ep_reward: -80.71962725489946, ep_step: 1000 +2023-05-26 13:58:11 - SimpleLog - INFO: - episode: 794, ep_reward: 309.4105119214005, ep_step: 1000 +2023-05-26 13:58:14 - SimpleLog - INFO: - episode: 795, ep_reward: 318.2235928760056, ep_step: 1000 +2023-05-26 13:58:16 - SimpleLog - INFO: - episode: 796, ep_reward: 295.90959619777277, ep_step: 1000 +2023-05-26 13:58:19 - SimpleLog - INFO: - episode: 797, ep_reward: -71.61796326556568, ep_step: 1000 +2023-05-26 13:58:21 - SimpleLog - INFO: - episode: 798, ep_reward: 368.08450414964074, ep_step: 1000 +2023-05-26 13:58:24 - SimpleLog - INFO: - episode: 799, ep_reward: 273.2215032676269, ep_step: 1000 +2023-05-26 13:58:26 - SimpleLog - INFO: - episode: 800, ep_reward: 407.05718615869756, ep_step: 1000 +2023-05-26 13:58:29 - SimpleLog - INFO: - episode: 801, ep_reward: 379.7322000501349, ep_step: 1000 +2023-05-26 13:58:31 - SimpleLog - INFO: - episode: 802, ep_reward: 155.3934670165179, ep_step: 1000 +2023-05-26 13:58:34 - SimpleLog - INFO: - episode: 803, ep_reward: 499.9721129805865, ep_step: 1000 +2023-05-26 13:58:36 - SimpleLog - INFO: - episode: 804, ep_reward: 389.29311768320076, ep_step: 1000 +2023-05-26 13:58:39 - SimpleLog - INFO: - episode: 805, ep_reward: 293.99603069959375, ep_step: 1000 +2023-05-26 13:58:41 - SimpleLog - INFO: - episode: 806, ep_reward: 203.4825779894233, ep_step: 1000 +2023-05-26 13:58:44 - SimpleLog - INFO: - episode: 807, ep_reward: -394.49119277707825, ep_step: 1000 +2023-05-26 13:58:46 - SimpleLog - INFO: - episode: 808, ep_reward: 319.26602896493006, ep_step: 1000 +2023-05-26 13:58:48 - SimpleLog - INFO: - episode: 809, ep_reward: 438.0747773513586, ep_step: 1000 +2023-05-26 13:58:51 - SimpleLog - INFO: - episode: 810, ep_reward: 166.30559155572845, ep_step: 1000 +2023-05-26 13:58:53 - SimpleLog - INFO: - episode: 811, ep_reward: 375.8498701739796, ep_step: 1000 +2023-05-26 13:58:56 - SimpleLog - INFO: - episode: 812, ep_reward: 521.0659227125727, ep_step: 1000 +2023-05-26 13:58:58 - SimpleLog - INFO: - episode: 813, ep_reward: 192.71855118376217, ep_step: 1000 +2023-05-26 13:59:01 - SimpleLog - INFO: - episode: 814, ep_reward: 412.8123165166658, ep_step: 1000 +2023-05-26 13:59:03 - SimpleLog - INFO: - episode: 815, ep_reward: 203.65126279287574, ep_step: 1000 +2023-05-26 13:59:05 - SimpleLog - INFO: - episode: 816, ep_reward: 446.650419711554, ep_step: 1000 +2023-05-26 13:59:08 - SimpleLog - INFO: - episode: 817, ep_reward: 527.7340622903348, ep_step: 1000 +2023-05-26 13:59:10 - SimpleLog - INFO: - episode: 818, ep_reward: 401.6785914647321, ep_step: 1000 +2023-05-26 13:59:13 - SimpleLog - INFO: - episode: 819, ep_reward: 277.7955908507874, ep_step: 1000 +2023-05-26 13:59:16 - SimpleLog - INFO: - episode: 820, ep_reward: 548.3820410632591, ep_step: 1000 +2023-05-26 13:59:18 - SimpleLog - INFO: - episode: 821, ep_reward: 459.876468097889, ep_step: 1000 +2023-05-26 13:59:21 - SimpleLog - INFO: - episode: 822, ep_reward: 371.2711465102037, ep_step: 1000 +2023-05-26 13:59:23 - SimpleLog - INFO: - episode: 823, ep_reward: 306.88114223246896, ep_step: 1000 +2023-05-26 13:59:26 - SimpleLog - INFO: - episode: 824, ep_reward: 295.99613251781125, ep_step: 1000 +2023-05-26 13:59:28 - SimpleLog - INFO: - episode: 825, ep_reward: 339.2715862167092, ep_step: 1000 +2023-05-26 13:59:31 - SimpleLog - INFO: - episode: 826, ep_reward: 524.226308029156, ep_step: 1000 +2023-05-26 13:59:33 - SimpleLog - INFO: - episode: 827, ep_reward: 483.9007326113821, ep_step: 1000 +2023-05-26 13:59:35 - SimpleLog - INFO: - episode: 828, ep_reward: 277.5950134363526, ep_step: 1000 +2023-05-26 13:59:38 - SimpleLog - INFO: - episode: 829, ep_reward: 270.7162923153394, ep_step: 1000 +2023-05-26 13:59:40 - SimpleLog - INFO: - episode: 830, ep_reward: 334.1455398631978, ep_step: 1000 +2023-05-26 13:59:43 - SimpleLog - INFO: - episode: 831, ep_reward: 326.3159014703915, ep_step: 1000 +2023-05-26 13:59:45 - SimpleLog - INFO: - episode: 832, ep_reward: 468.58011616537414, ep_step: 1000 +2023-05-26 13:59:47 - SimpleLog - INFO: - episode: 833, ep_reward: 325.09951615014177, ep_step: 1000 +2023-05-26 13:59:50 - SimpleLog - INFO: - episode: 834, ep_reward: 325.8231251042024, ep_step: 1000 +2023-05-26 13:59:52 - SimpleLog - INFO: - episode: 835, ep_reward: 249.2637410102155, ep_step: 1000 +2023-05-26 13:59:55 - SimpleLog - INFO: - episode: 836, ep_reward: 115.5630789565976, ep_step: 1000 +2023-05-26 13:59:57 - SimpleLog - INFO: - episode: 837, ep_reward: 307.1695335322578, ep_step: 1000 +2023-05-26 14:00:00 - SimpleLog - INFO: - episode: 838, ep_reward: 382.81312299884246, ep_step: 1000 +2023-05-26 14:00:02 - SimpleLog - INFO: - episode: 839, ep_reward: 492.59970555292534, ep_step: 1000 +2023-05-26 14:00:05 - SimpleLog - INFO: - episode: 840, ep_reward: 504.0963586024561, ep_step: 1000 +2023-05-26 14:00:07 - SimpleLog - INFO: - episode: 841, ep_reward: 191.52823762472474, ep_step: 1000 +2023-05-26 14:00:09 - SimpleLog - INFO: - episode: 842, ep_reward: 285.2458662910536, ep_step: 1000 +2023-05-26 14:00:12 - SimpleLog - INFO: - episode: 843, ep_reward: 476.0833257343271, ep_step: 1000 +2023-05-26 14:00:14 - SimpleLog - INFO: - episode: 844, ep_reward: 500.65548790191997, ep_step: 1000 +2023-05-26 14:00:17 - SimpleLog - INFO: - episode: 845, ep_reward: 479.4999367023625, ep_step: 1000 +2023-05-26 14:00:19 - SimpleLog - INFO: - episode: 846, ep_reward: 302.3477039104893, ep_step: 1000 +2023-05-26 14:00:22 - SimpleLog - INFO: - episode: 847, ep_reward: 500.15824398323053, ep_step: 1000 +2023-05-26 14:00:24 - SimpleLog - INFO: - episode: 848, ep_reward: 464.43577784725414, ep_step: 1000 +2023-05-26 14:00:27 - SimpleLog - INFO: - episode: 849, ep_reward: 315.97511515743656, ep_step: 1000 +2023-05-26 14:00:30 - SimpleLog - INFO: - episode: 850, ep_reward: 310.3657628061669, ep_step: 1000 +2023-05-26 14:00:32 - SimpleLog - INFO: - episode: 851, ep_reward: 537.0290661345387, ep_step: 1000 +2023-05-26 14:00:35 - SimpleLog - INFO: - episode: 852, ep_reward: 390.395097998832, ep_step: 1000 +2023-05-26 14:00:37 - SimpleLog - INFO: - episode: 853, ep_reward: 408.82788703989894, ep_step: 1000 +2023-05-26 14:00:39 - SimpleLog - INFO: - episode: 854, ep_reward: 365.42661095959795, ep_step: 1000 +2023-05-26 14:00:42 - SimpleLog - INFO: - episode: 855, ep_reward: 330.5793673823342, ep_step: 1000 +2023-05-26 14:00:44 - SimpleLog - INFO: - episode: 856, ep_reward: 554.6320748000319, ep_step: 1000 +2023-05-26 14:00:47 - SimpleLog - INFO: - episode: 857, ep_reward: 249.3969530139839, ep_step: 1000 +2023-05-26 14:00:49 - SimpleLog - INFO: - episode: 858, ep_reward: 640.7629078634059, ep_step: 1000 +2023-05-26 14:00:52 - SimpleLog - INFO: - episode: 859, ep_reward: 456.4113826986321, ep_step: 1000 +2023-05-26 14:00:54 - SimpleLog - INFO: - episode: 860, ep_reward: 784.6576920414201, ep_step: 1000 +2023-05-26 14:00:57 - SimpleLog - INFO: - episode: 861, ep_reward: 414.2744189600687, ep_step: 1000 +2023-05-26 14:01:00 - SimpleLog - INFO: - episode: 862, ep_reward: 151.6819743959805, ep_step: 1000 +2023-05-26 14:01:02 - SimpleLog - INFO: - episode: 863, ep_reward: 454.25227370933493, ep_step: 1000 +2023-05-26 14:01:04 - SimpleLog - INFO: - episode: 864, ep_reward: 624.040768949367, ep_step: 1000 +2023-05-26 14:01:07 - SimpleLog - INFO: - episode: 865, ep_reward: 556.4840194922135, ep_step: 1000 +2023-05-26 14:01:09 - SimpleLog - INFO: - episode: 866, ep_reward: 501.8306780852112, ep_step: 1000 +2023-05-26 14:01:12 - SimpleLog - INFO: - episode: 867, ep_reward: 487.58385374007827, ep_step: 1000 +2023-05-26 14:01:14 - SimpleLog - INFO: - episode: 868, ep_reward: 666.2419371570264, ep_step: 1000 +2023-05-26 14:01:17 - SimpleLog - INFO: - episode: 869, ep_reward: 510.81133945999, ep_step: 1000 +2023-05-26 14:01:19 - SimpleLog - INFO: - episode: 870, ep_reward: 555.1848925037312, ep_step: 1000 +2023-05-26 14:01:22 - SimpleLog - INFO: - episode: 871, ep_reward: 605.4387426740527, ep_step: 1000 +2023-05-26 14:01:24 - SimpleLog - INFO: - episode: 872, ep_reward: 493.8436128114499, ep_step: 1000 +2023-05-26 14:01:27 - SimpleLog - INFO: - episode: 873, ep_reward: 383.4240554573677, ep_step: 1000 +2023-05-26 14:01:29 - SimpleLog - INFO: - episode: 874, ep_reward: 395.8067561158325, ep_step: 1000 +2023-05-26 14:01:32 - SimpleLog - INFO: - episode: 875, ep_reward: 602.979779575626, ep_step: 1000 +2023-05-26 14:01:34 - SimpleLog - INFO: - episode: 876, ep_reward: 597.8814379200741, ep_step: 1000 +2023-05-26 14:01:37 - SimpleLog - INFO: - episode: 877, ep_reward: 200.18333093947805, ep_step: 1000 +2023-05-26 14:01:39 - SimpleLog - INFO: - episode: 878, ep_reward: 353.3583403901296, ep_step: 1000 +2023-05-26 14:01:41 - SimpleLog - INFO: - episode: 879, ep_reward: 489.25505424875377, ep_step: 1000 +2023-05-26 14:01:44 - SimpleLog - INFO: - episode: 880, ep_reward: 521.9087880362026, ep_step: 1000 +2023-05-26 14:01:46 - SimpleLog - INFO: - episode: 881, ep_reward: 754.6774795453417, ep_step: 1000 +2023-05-26 14:01:49 - SimpleLog - INFO: - episode: 882, ep_reward: 363.70349971229956, ep_step: 1000 +2023-05-26 14:01:51 - SimpleLog - INFO: - episode: 883, ep_reward: 666.656889569618, ep_step: 1000 +2023-05-26 14:01:54 - SimpleLog - INFO: - episode: 884, ep_reward: 326.689555602108, ep_step: 1000 +2023-05-26 14:01:56 - SimpleLog - INFO: - episode: 885, ep_reward: 635.8020681508499, ep_step: 1000 +2023-05-26 14:01:58 - SimpleLog - INFO: - episode: 886, ep_reward: 475.8332004824074, ep_step: 1000 +2023-05-26 14:02:01 - SimpleLog - INFO: - episode: 887, ep_reward: 345.8928933960638, ep_step: 1000 +2023-05-26 14:02:03 - SimpleLog - INFO: - episode: 888, ep_reward: 337.6776578736113, ep_step: 1000 +2023-05-26 14:02:06 - SimpleLog - INFO: - episode: 889, ep_reward: 520.5374234952957, ep_step: 1000 +2023-05-26 14:02:08 - SimpleLog - INFO: - episode: 890, ep_reward: 144.57294268431946, ep_step: 1000 +2023-05-26 14:02:11 - SimpleLog - INFO: - episode: 891, ep_reward: 403.6525029995994, ep_step: 1000 +2023-05-26 14:02:13 - SimpleLog - INFO: - episode: 892, ep_reward: 418.461535395275, ep_step: 1000 +2023-05-26 14:02:16 - SimpleLog - INFO: - episode: 893, ep_reward: 514.6185263583222, ep_step: 1000 +2023-05-26 14:02:18 - SimpleLog - INFO: - episode: 894, ep_reward: 396.82604473363835, ep_step: 1000 +2023-05-26 14:02:27 - SimpleLog - INFO: - update_step: 3500, online_eval_reward: 471.131 +2023-05-26 14:02:27 - SimpleLog - INFO: - episode: 895, ep_reward: 404.15689850302596, ep_step: 1000 +2023-05-26 14:02:28 - SimpleLog - INFO: - episode: 896, ep_reward: 508.762643389517, ep_step: 1000 +2023-05-26 14:02:30 - SimpleLog - INFO: - episode: 897, ep_reward: 367.6845888665611, ep_step: 1000 +2023-05-26 14:02:33 - SimpleLog - INFO: - episode: 898, ep_reward: 603.4696629761314, ep_step: 1000 +2023-05-26 14:02:35 - SimpleLog - INFO: - episode: 899, ep_reward: 434.9241035404068, ep_step: 1000 +2023-05-26 14:02:38 - SimpleLog - INFO: - episode: 900, ep_reward: 469.5396180326878, ep_step: 1000 +2023-05-26 14:02:40 - SimpleLog - INFO: - episode: 901, ep_reward: 618.2458306017293, ep_step: 1000 +2023-05-26 14:02:43 - SimpleLog - INFO: - episode: 902, ep_reward: 525.9449027932269, ep_step: 1000 +2023-05-26 14:02:45 - SimpleLog - INFO: - episode: 903, ep_reward: 673.0625334943588, ep_step: 1000 +2023-05-26 14:02:47 - SimpleLog - INFO: - episode: 904, ep_reward: 512.5694198542844, ep_step: 1000 +2023-05-26 14:02:50 - SimpleLog - INFO: - episode: 905, ep_reward: 420.86560660735995, ep_step: 1000 +2023-05-26 14:02:52 - SimpleLog - INFO: - episode: 906, ep_reward: 399.65783372151037, ep_step: 1000 +2023-05-26 14:02:55 - SimpleLog - INFO: - episode: 907, ep_reward: 657.343898724644, ep_step: 1000 +2023-05-26 14:02:57 - SimpleLog - INFO: - episode: 908, ep_reward: 761.228416887866, ep_step: 1000 +2023-05-26 14:03:00 - SimpleLog - INFO: - episode: 909, ep_reward: 420.6878769604668, ep_step: 1000 +2023-05-26 14:03:02 - SimpleLog - INFO: - episode: 910, ep_reward: 439.0867701884528, ep_step: 1000 +2023-05-26 14:03:05 - SimpleLog - INFO: - episode: 911, ep_reward: 601.3421585815894, ep_step: 1000 +2023-05-26 14:03:07 - SimpleLog - INFO: - episode: 912, ep_reward: 464.74390730127305, ep_step: 1000 +2023-05-26 14:03:10 - SimpleLog - INFO: - episode: 913, ep_reward: 777.1240924085996, ep_step: 1000 +2023-05-26 14:03:12 - SimpleLog - INFO: - episode: 914, ep_reward: 255.99473012856456, ep_step: 1000 +2023-05-26 14:03:15 - SimpleLog - INFO: - episode: 915, ep_reward: 443.99251398844797, ep_step: 1000 +2023-05-26 14:03:17 - SimpleLog - INFO: - episode: 916, ep_reward: 568.7340553800229, ep_step: 1000 +2023-05-26 14:03:20 - SimpleLog - INFO: - episode: 917, ep_reward: 626.1272573739285, ep_step: 1000 +2023-05-26 14:03:22 - SimpleLog - INFO: - episode: 918, ep_reward: 432.48544507787824, ep_step: 1000 +2023-05-26 14:03:25 - SimpleLog - INFO: - episode: 919, ep_reward: 459.48595840848026, ep_step: 1000 +2023-05-26 14:03:27 - SimpleLog - INFO: - episode: 920, ep_reward: 513.0997442718184, ep_step: 1000 +2023-05-26 14:03:30 - SimpleLog - INFO: - episode: 921, ep_reward: 326.2505875687104, ep_step: 1000 +2023-05-26 14:03:32 - SimpleLog - INFO: - episode: 922, ep_reward: 458.12552599190775, ep_step: 1000 +2023-05-26 14:03:35 - SimpleLog - INFO: - episode: 923, ep_reward: 159.83856610228133, ep_step: 1000 +2023-05-26 14:03:37 - SimpleLog - INFO: - episode: 924, ep_reward: 564.5143740989765, ep_step: 1000 +2023-05-26 14:03:40 - SimpleLog - INFO: - episode: 925, ep_reward: 553.4195575460589, ep_step: 1000 +2023-05-26 14:03:42 - SimpleLog - INFO: - episode: 926, ep_reward: 602.585131332956, ep_step: 1000 +2023-05-26 14:03:45 - SimpleLog - INFO: - episode: 927, ep_reward: 795.9900034656804, ep_step: 1000 +2023-05-26 14:03:48 - SimpleLog - INFO: - episode: 928, ep_reward: 453.01871223382904, ep_step: 1000 +2023-05-26 14:03:50 - SimpleLog - INFO: - episode: 929, ep_reward: 444.5661877768358, ep_step: 1000 +2023-05-26 14:03:53 - SimpleLog - INFO: - episode: 930, ep_reward: 458.28836582079947, ep_step: 1000 +2023-05-26 14:03:55 - SimpleLog - INFO: - episode: 931, ep_reward: 363.11632768576936, ep_step: 1000 +2023-05-26 14:03:58 - SimpleLog - INFO: - episode: 932, ep_reward: 599.9378200347991, ep_step: 1000 +2023-05-26 14:04:00 - SimpleLog - INFO: - episode: 933, ep_reward: 655.493069861295, ep_step: 1000 +2023-05-26 14:04:03 - SimpleLog - INFO: - episode: 934, ep_reward: 251.40636071647177, ep_step: 1000 +2023-05-26 14:04:06 - SimpleLog - INFO: - episode: 935, ep_reward: 331.3885035507152, ep_step: 1000 +2023-05-26 14:04:09 - SimpleLog - INFO: - episode: 936, ep_reward: 487.2679451606658, ep_step: 1000 +2023-05-26 14:04:12 - SimpleLog - INFO: - episode: 937, ep_reward: 928.7108148185156, ep_step: 1000 +2023-05-26 14:04:15 - SimpleLog - INFO: - episode: 938, ep_reward: 232.0828303961315, ep_step: 1000 +2023-05-26 14:04:18 - SimpleLog - INFO: - episode: 939, ep_reward: 365.475352059893, ep_step: 1000 +2023-05-26 14:04:21 - SimpleLog - INFO: - episode: 940, ep_reward: 533.5191825302926, ep_step: 1000 +2023-05-26 14:04:24 - SimpleLog - INFO: - episode: 941, ep_reward: 293.2759969593935, ep_step: 1000 +2023-05-26 14:04:27 - SimpleLog - INFO: - episode: 942, ep_reward: 547.7871711905871, ep_step: 1000 +2023-05-26 14:04:30 - SimpleLog - INFO: - episode: 943, ep_reward: 388.96343587753375, ep_step: 1000 +2023-05-26 14:04:33 - SimpleLog - INFO: - episode: 944, ep_reward: 541.4626262964614, ep_step: 1000 +2023-05-26 14:04:36 - SimpleLog - INFO: - episode: 945, ep_reward: 394.8777492388698, ep_step: 1000 +2023-05-26 14:04:39 - SimpleLog - INFO: - episode: 946, ep_reward: 511.6738073157001, ep_step: 1000 +2023-05-26 14:04:42 - SimpleLog - INFO: - episode: 947, ep_reward: 615.2441181186914, ep_step: 1000 +2023-05-26 14:04:45 - SimpleLog - INFO: - episode: 948, ep_reward: 331.571478128236, ep_step: 1000 +2023-05-26 14:04:48 - SimpleLog - INFO: - episode: 949, ep_reward: 615.7526504105634, ep_step: 1000 +2023-05-26 14:04:51 - SimpleLog - INFO: - episode: 950, ep_reward: 479.54284354069125, ep_step: 1000 +2023-05-26 14:04:54 - SimpleLog - INFO: - episode: 951, ep_reward: 101.53637111660525, ep_step: 1000 +2023-05-26 14:04:58 - SimpleLog - INFO: - episode: 952, ep_reward: 573.4746966734613, ep_step: 1000 +2023-05-26 14:05:01 - SimpleLog - INFO: - episode: 953, ep_reward: 1051.148844597714, ep_step: 1000 +2023-05-26 14:05:04 - SimpleLog - INFO: - episode: 954, ep_reward: 515.1850618978209, ep_step: 1000 +2023-05-26 14:05:07 - SimpleLog - INFO: - episode: 955, ep_reward: 423.64952364696194, ep_step: 1000 +2023-05-26 14:05:10 - SimpleLog - INFO: - episode: 956, ep_reward: 626.5348082912033, ep_step: 1000 +2023-05-26 14:05:13 - SimpleLog - INFO: - episode: 957, ep_reward: 263.8174905238898, ep_step: 1000 +2023-05-26 14:05:16 - SimpleLog - INFO: - episode: 958, ep_reward: 879.4815699540619, ep_step: 1000 +2023-05-26 14:05:19 - SimpleLog - INFO: - episode: 959, ep_reward: 241.91495908140743, ep_step: 1000 +2023-05-26 14:05:22 - SimpleLog - INFO: - episode: 960, ep_reward: 479.1848827772257, ep_step: 1000 +2023-05-26 14:05:25 - SimpleLog - INFO: - episode: 961, ep_reward: 861.7542878787547, ep_step: 1000 +2023-05-26 14:05:28 - SimpleLog - INFO: - episode: 962, ep_reward: 374.99618925785495, ep_step: 1000 +2023-05-26 14:05:31 - SimpleLog - INFO: - episode: 963, ep_reward: 571.1142520046138, ep_step: 1000 +2023-05-26 14:05:34 - SimpleLog - INFO: - episode: 964, ep_reward: 329.4104303558809, ep_step: 1000 +2023-05-26 14:05:37 - SimpleLog - INFO: - episode: 965, ep_reward: 342.6156623916169, ep_step: 1000 +2023-05-26 14:05:40 - SimpleLog - INFO: - episode: 966, ep_reward: 320.19981949594774, ep_step: 1000 +2023-05-26 14:05:43 - SimpleLog - INFO: - episode: 967, ep_reward: 793.0849224018027, ep_step: 1000 +2023-05-26 14:05:46 - SimpleLog - INFO: - episode: 968, ep_reward: 511.07851672297755, ep_step: 1000 +2023-05-26 14:05:49 - SimpleLog - INFO: - episode: 969, ep_reward: 564.748653177202, ep_step: 1000 +2023-05-26 14:05:52 - SimpleLog - INFO: - episode: 970, ep_reward: 241.03475031104412, ep_step: 1000 +2023-05-26 14:05:55 - SimpleLog - INFO: - episode: 971, ep_reward: 856.0831278551486, ep_step: 1000 +2023-05-26 14:05:59 - SimpleLog - INFO: - episode: 972, ep_reward: 393.0920104488221, ep_step: 1000 +2023-05-26 14:06:02 - SimpleLog - INFO: - episode: 973, ep_reward: 651.8357854875558, ep_step: 1000 +2023-05-26 14:06:05 - SimpleLog - INFO: - episode: 974, ep_reward: 489.44639515041393, ep_step: 1000 +2023-05-26 14:06:08 - SimpleLog - INFO: - episode: 975, ep_reward: 533.3050874432007, ep_step: 1000 +2023-05-26 14:06:10 - SimpleLog - INFO: - episode: 976, ep_reward: 631.8078927999002, ep_step: 1000 +2023-05-26 14:06:13 - SimpleLog - INFO: - episode: 977, ep_reward: 517.7123723545523, ep_step: 1000 +2023-05-26 14:06:15 - SimpleLog - INFO: - episode: 978, ep_reward: 449.64673261199914, ep_step: 1000 +2023-05-26 14:06:18 - SimpleLog - INFO: - episode: 979, ep_reward: 242.32716274225783, ep_step: 1000 +2023-05-26 14:06:20 - SimpleLog - INFO: - episode: 980, ep_reward: 445.53531227733606, ep_step: 1000 +2023-05-26 14:06:23 - SimpleLog - INFO: - episode: 981, ep_reward: 176.3298832447627, ep_step: 1000 +2023-05-26 14:06:25 - SimpleLog - INFO: - episode: 982, ep_reward: 443.71025835155956, ep_step: 1000 +2023-05-26 14:06:27 - SimpleLog - INFO: - episode: 983, ep_reward: 627.6342864620624, ep_step: 1000 +2023-05-26 14:06:30 - SimpleLog - INFO: - episode: 984, ep_reward: 195.09830196410812, ep_step: 1000 +2023-05-26 14:06:32 - SimpleLog - INFO: - episode: 985, ep_reward: 582.162058734231, ep_step: 1000 +2023-05-26 14:06:35 - SimpleLog - INFO: - episode: 986, ep_reward: 318.0113004217189, ep_step: 1000 +2023-05-26 14:06:37 - SimpleLog - INFO: - episode: 987, ep_reward: 433.43180805362243, ep_step: 1000 +2023-05-26 14:06:40 - SimpleLog - INFO: - episode: 988, ep_reward: 288.6115065076913, ep_step: 1000 +2023-05-26 14:06:42 - SimpleLog - INFO: - episode: 989, ep_reward: 178.50022927959202, ep_step: 1000 +2023-05-26 14:06:45 - SimpleLog - INFO: - episode: 990, ep_reward: 443.1227601898511, ep_step: 1000 +2023-05-26 14:06:47 - SimpleLog - INFO: - episode: 991, ep_reward: 41.50478301482156, ep_step: 1000 +2023-05-26 14:06:49 - SimpleLog - INFO: - episode: 992, ep_reward: 416.99005110626643, ep_step: 1000 +2023-05-26 14:06:52 - SimpleLog - INFO: - episode: 993, ep_reward: 421.0607835235016, ep_step: 1000 +2023-05-26 14:06:54 - SimpleLog - INFO: - episode: 994, ep_reward: 419.8114898405762, ep_step: 1000 +2023-05-26 14:06:56 - SimpleLog - INFO: - episode: 995, ep_reward: 399.176822380154, ep_step: 1000 +2023-05-26 14:06:59 - SimpleLog - INFO: - episode: 996, ep_reward: 522.1143697997043, ep_step: 1000 +2023-05-26 14:07:01 - SimpleLog - INFO: - episode: 997, ep_reward: 238.13939273107079, ep_step: 1000 +2023-05-26 14:07:04 - SimpleLog - INFO: - episode: 998, ep_reward: 400.3786975959656, ep_step: 1000 +2023-05-26 14:07:06 - SimpleLog - INFO: - episode: 999, ep_reward: 238.5588532456164, ep_step: 1000 +2023-05-26 14:07:08 - SimpleLog - INFO: - episode: 1000, ep_reward: 323.6491975911785, ep_step: 1000 +2023-05-26 14:07:11 - SimpleLog - INFO: - episode: 1001, ep_reward: 631.0583717366026, ep_step: 1000 +2023-05-26 14:07:13 - SimpleLog - INFO: - episode: 1002, ep_reward: 399.5399646871972, ep_step: 1000 +2023-05-26 14:07:15 - SimpleLog - INFO: - episode: 1003, ep_reward: 158.02888422646143, ep_step: 1000 +2023-05-26 14:07:18 - SimpleLog - INFO: - episode: 1004, ep_reward: 427.7454011936308, ep_step: 1000 +2023-05-26 14:07:20 - SimpleLog - INFO: - episode: 1005, ep_reward: 510.39117210084686, ep_step: 1000 +2023-05-26 14:07:22 - SimpleLog - INFO: - episode: 1006, ep_reward: 233.19951080793686, ep_step: 1000 +2023-05-26 14:07:24 - SimpleLog - INFO: - episode: 1007, ep_reward: 472.1233464366899, ep_step: 1000 +2023-05-26 14:07:27 - SimpleLog - INFO: - episode: 1008, ep_reward: 298.36747269053745, ep_step: 1000 +2023-05-26 14:07:29 - SimpleLog - INFO: - episode: 1009, ep_reward: 361.8881801424895, ep_step: 1000 +2023-05-26 14:07:31 - SimpleLog - INFO: - episode: 1010, ep_reward: 122.81793820699917, ep_step: 1000 +2023-05-26 14:07:34 - SimpleLog - INFO: - episode: 1011, ep_reward: 548.3245942413599, ep_step: 1000 +2023-05-26 14:07:36 - SimpleLog - INFO: - episode: 1012, ep_reward: 502.02955986807586, ep_step: 1000 +2023-05-26 14:07:38 - SimpleLog - INFO: - episode: 1013, ep_reward: -419.13470807665965, ep_step: 1000 +2023-05-26 14:07:41 - SimpleLog - INFO: - episode: 1014, ep_reward: 143.1453941775273, ep_step: 1000 +2023-05-26 14:07:43 - SimpleLog - INFO: - episode: 1015, ep_reward: 124.57734547982005, ep_step: 1000 +2023-05-26 14:07:45 - SimpleLog - INFO: - episode: 1016, ep_reward: 459.0759098008882, ep_step: 1000 +2023-05-26 14:07:47 - SimpleLog - INFO: - episode: 1017, ep_reward: 669.1137219129629, ep_step: 1000 +2023-05-26 14:07:50 - SimpleLog - INFO: - episode: 1018, ep_reward: 451.0919675000852, ep_step: 1000 +2023-05-26 14:07:52 - SimpleLog - INFO: - episode: 1019, ep_reward: 440.76352697948323, ep_step: 1000 +2023-05-26 14:07:54 - SimpleLog - INFO: - episode: 1020, ep_reward: 533.6409883719422, ep_step: 1000 +2023-05-26 14:07:57 - SimpleLog - INFO: - episode: 1021, ep_reward: 428.3702778250103, ep_step: 1000 +2023-05-26 14:07:59 - SimpleLog - INFO: - episode: 1022, ep_reward: 518.853362302607, ep_step: 1000 +2023-05-26 14:08:07 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: 672.788 +2023-05-26 14:08:07 - SimpleLog - INFO: - episode: 1023, ep_reward: 478.83494854075815, ep_step: 1000 +2023-05-26 14:08:09 - SimpleLog - INFO: - episode: 1024, ep_reward: 501.9496087595801, ep_step: 1000 +2023-05-26 14:08:11 - SimpleLog - INFO: - episode: 1025, ep_reward: 591.9594225243993, ep_step: 1000 +2023-05-26 14:08:13 - SimpleLog - INFO: - episode: 1026, ep_reward: 520.4283457755181, ep_step: 1000 +2023-05-26 14:08:15 - SimpleLog - INFO: - episode: 1027, ep_reward: 535.2882339166791, ep_step: 1000 +2023-05-26 14:08:18 - SimpleLog - INFO: - episode: 1028, ep_reward: 250.79356394973962, ep_step: 1000 +2023-05-26 14:08:20 - SimpleLog - INFO: - episode: 1029, ep_reward: 438.521527979875, ep_step: 1000 +2023-05-26 14:08:22 - SimpleLog - INFO: - episode: 1030, ep_reward: 657.7678927901851, ep_step: 1000 +2023-05-26 14:08:25 - SimpleLog - INFO: - episode: 1031, ep_reward: 345.47732305018553, ep_step: 1000 +2023-05-26 14:08:27 - SimpleLog - INFO: - episode: 1032, ep_reward: 499.0035835169092, ep_step: 1000 +2023-05-26 14:08:29 - SimpleLog - INFO: - episode: 1033, ep_reward: 357.491515765271, ep_step: 1000 +2023-05-26 14:08:31 - SimpleLog - INFO: - episode: 1034, ep_reward: 443.3843804295934, ep_step: 1000 +2023-05-26 14:08:34 - SimpleLog - INFO: - episode: 1035, ep_reward: 407.16650088735247, ep_step: 1000 +2023-05-26 14:08:36 - SimpleLog - INFO: - episode: 1036, ep_reward: 510.63883378988487, ep_step: 1000 +2023-05-26 14:08:39 - SimpleLog - INFO: - episode: 1037, ep_reward: 541.0083903109818, ep_step: 1000 +2023-05-26 14:08:41 - SimpleLog - INFO: - episode: 1038, ep_reward: 665.5946897798827, ep_step: 1000 +2023-05-26 14:08:43 - SimpleLog - INFO: - episode: 1039, ep_reward: 234.05501424282218, ep_step: 1000 +2023-05-26 14:08:46 - SimpleLog - INFO: - episode: 1040, ep_reward: 568.2571863161696, ep_step: 1000 +2023-05-26 14:08:48 - SimpleLog - INFO: - episode: 1041, ep_reward: 653.7576581567075, ep_step: 1000 +2023-05-26 14:08:51 - SimpleLog - INFO: - episode: 1042, ep_reward: 605.3018348591376, ep_step: 1000 +2023-05-26 14:08:53 - SimpleLog - INFO: - episode: 1043, ep_reward: -232.52795629970225, ep_step: 1000 +2023-05-26 14:08:55 - SimpleLog - INFO: - episode: 1044, ep_reward: -157.7397699761291, ep_step: 1000 +2023-05-26 14:08:57 - SimpleLog - INFO: - episode: 1045, ep_reward: 14.87182254040219, ep_step: 1000 +2023-05-26 14:09:00 - SimpleLog - INFO: - episode: 1046, ep_reward: 172.33702797532226, ep_step: 1000 +2023-05-26 14:09:02 - SimpleLog - INFO: - episode: 1047, ep_reward: 527.8866814989555, ep_step: 1000 +2023-05-26 14:09:04 - SimpleLog - INFO: - episode: 1048, ep_reward: 463.3719110825244, ep_step: 1000 +2023-05-26 14:09:07 - SimpleLog - INFO: - episode: 1049, ep_reward: 471.9528237272086, ep_step: 1000 +2023-05-26 14:09:09 - SimpleLog - INFO: - episode: 1050, ep_reward: 398.89352880538695, ep_step: 1000 +2023-05-26 14:09:11 - SimpleLog - INFO: - episode: 1051, ep_reward: 443.3467972653826, ep_step: 1000 +2023-05-26 14:09:13 - SimpleLog - INFO: - episode: 1052, ep_reward: 484.2139178811134, ep_step: 1000 +2023-05-26 14:09:16 - SimpleLog - INFO: - episode: 1053, ep_reward: 528.9688332149939, ep_step: 1000 +2023-05-26 14:09:19 - SimpleLog - INFO: - episode: 1054, ep_reward: 439.7356358368308, ep_step: 1000 +2023-05-26 14:09:21 - SimpleLog - INFO: - episode: 1055, ep_reward: 472.1861636485287, ep_step: 1000 +2023-05-26 14:09:23 - SimpleLog - INFO: - episode: 1056, ep_reward: 451.5693394899175, ep_step: 1000 +2023-05-26 14:09:26 - SimpleLog - INFO: - episode: 1057, ep_reward: 586.6025313977315, ep_step: 1000 +2023-05-26 14:09:28 - SimpleLog - INFO: - episode: 1058, ep_reward: 511.08478642738856, ep_step: 1000 +2023-05-26 14:09:30 - SimpleLog - INFO: - episode: 1059, ep_reward: 570.4461238971807, ep_step: 1000 +2023-05-26 14:09:33 - SimpleLog - INFO: - episode: 1060, ep_reward: 425.8272986564808, ep_step: 1000 +2023-05-26 14:09:35 - SimpleLog - INFO: - episode: 1061, ep_reward: 695.0984616350191, ep_step: 1000 +2023-05-26 14:09:37 - SimpleLog - INFO: - episode: 1062, ep_reward: 486.86260100961744, ep_step: 1000 +2023-05-26 14:09:40 - SimpleLog - INFO: - episode: 1063, ep_reward: 564.0534559260126, ep_step: 1000 +2023-05-26 14:09:42 - SimpleLog - INFO: - episode: 1064, ep_reward: 559.5728172114468, ep_step: 1000 +2023-05-26 14:09:44 - SimpleLog - INFO: - episode: 1065, ep_reward: 624.589824214696, ep_step: 1000 +2023-05-26 14:09:47 - SimpleLog - INFO: - episode: 1066, ep_reward: 492.5718468708911, ep_step: 1000 +2023-05-26 14:09:49 - SimpleLog - INFO: - episode: 1067, ep_reward: 509.6261802893905, ep_step: 1000 +2023-05-26 14:09:51 - SimpleLog - INFO: - episode: 1068, ep_reward: 195.82398573878223, ep_step: 1000 +2023-05-26 14:09:54 - SimpleLog - INFO: - episode: 1069, ep_reward: 552.0410239373668, ep_step: 1000 +2023-05-26 14:09:56 - SimpleLog - INFO: - episode: 1070, ep_reward: 533.4415033646384, ep_step: 1000 +2023-05-26 14:09:58 - SimpleLog - INFO: - episode: 1071, ep_reward: 547.8711651010884, ep_step: 1000 +2023-05-26 14:10:01 - SimpleLog - INFO: - episode: 1072, ep_reward: 481.547260797352, ep_step: 1000 +2023-05-26 14:10:03 - SimpleLog - INFO: - episode: 1073, ep_reward: 409.0509781060366, ep_step: 1000 +2023-05-26 14:10:05 - SimpleLog - INFO: - episode: 1074, ep_reward: 517.7347982681504, ep_step: 1000 +2023-05-26 14:10:08 - SimpleLog - INFO: - episode: 1075, ep_reward: 390.11408834694936, ep_step: 1000 +2023-05-26 14:10:10 - SimpleLog - INFO: - episode: 1076, ep_reward: 531.5880821194888, ep_step: 1000 +2023-05-26 14:10:13 - SimpleLog - INFO: - episode: 1077, ep_reward: 462.91298605680197, ep_step: 1000 +2023-05-26 14:10:15 - SimpleLog - INFO: - episode: 1078, ep_reward: 484.887206320582, ep_step: 1000 +2023-05-26 14:10:17 - SimpleLog - INFO: - episode: 1079, ep_reward: 349.1485682159426, ep_step: 1000 +2023-05-26 14:10:20 - SimpleLog - INFO: - episode: 1080, ep_reward: 533.8518347924955, ep_step: 1000 +2023-05-26 14:10:22 - SimpleLog - INFO: - episode: 1081, ep_reward: 448.38858071214855, ep_step: 1000 +2023-05-26 14:10:25 - SimpleLog - INFO: - episode: 1082, ep_reward: 255.37665610042532, ep_step: 1000 +2023-05-26 14:10:27 - SimpleLog - INFO: - episode: 1083, ep_reward: 662.314326657578, ep_step: 1000 +2023-05-26 14:10:30 - SimpleLog - INFO: - episode: 1084, ep_reward: 421.0951925691432, ep_step: 1000 +2023-05-26 14:10:32 - SimpleLog - INFO: - episode: 1085, ep_reward: 569.2483284467767, ep_step: 1000 +2023-05-26 14:10:35 - SimpleLog - INFO: - episode: 1086, ep_reward: 473.127630564151, ep_step: 1000 +2023-05-26 14:10:37 - SimpleLog - INFO: - episode: 1087, ep_reward: 647.2559821171029, ep_step: 1000 +2023-05-26 14:10:39 - SimpleLog - INFO: - episode: 1088, ep_reward: 121.90735999517973, ep_step: 1000 +2023-05-26 14:10:42 - SimpleLog - INFO: - episode: 1089, ep_reward: 561.1909655357632, ep_step: 1000 +2023-05-26 14:10:44 - SimpleLog - INFO: - episode: 1090, ep_reward: 494.1128070804326, ep_step: 1000 +2023-05-26 14:10:46 - SimpleLog - INFO: - episode: 1091, ep_reward: 283.825554201136, ep_step: 1000 +2023-05-26 14:10:48 - SimpleLog - INFO: - episode: 1092, ep_reward: 243.79688005251342, ep_step: 1000 +2023-05-26 14:10:51 - SimpleLog - INFO: - episode: 1093, ep_reward: 345.4217951259481, ep_step: 1000 +2023-05-26 14:10:53 - SimpleLog - INFO: - episode: 1094, ep_reward: 488.98769740166773, ep_step: 1000 +2023-05-26 14:10:55 - SimpleLog - INFO: - episode: 1095, ep_reward: 508.4857812647564, ep_step: 1000 +2023-05-26 14:10:58 - SimpleLog - INFO: - episode: 1096, ep_reward: 483.886674421391, ep_step: 1000 +2023-05-26 14:11:00 - SimpleLog - INFO: - episode: 1097, ep_reward: 597.6680562611605, ep_step: 1000 +2023-05-26 14:11:02 - SimpleLog - INFO: - episode: 1098, ep_reward: 654.3006226668823, ep_step: 1000 +2023-05-26 14:11:04 - SimpleLog - INFO: - episode: 1099, ep_reward: 452.564972634681, ep_step: 1000 +2023-05-26 14:11:07 - SimpleLog - INFO: - episode: 1100, ep_reward: 658.9735010789379, ep_step: 1000 +2023-05-26 14:11:09 - SimpleLog - INFO: - episode: 1101, ep_reward: 407.7756933331115, ep_step: 1000 +2023-05-26 14:11:11 - SimpleLog - INFO: - episode: 1102, ep_reward: 186.1122024666511, ep_step: 1000 +2023-05-26 14:11:14 - SimpleLog - INFO: - episode: 1103, ep_reward: 484.4267942890032, ep_step: 1000 +2023-05-26 14:11:16 - SimpleLog - INFO: - episode: 1104, ep_reward: 750.6066429180554, ep_step: 1000 +2023-05-26 14:11:18 - SimpleLog - INFO: - episode: 1105, ep_reward: 499.2545583431784, ep_step: 1000 +2023-05-26 14:11:20 - SimpleLog - INFO: - episode: 1106, ep_reward: 339.59122758750686, ep_step: 1000 +2023-05-26 14:11:23 - SimpleLog - INFO: - episode: 1107, ep_reward: 582.9592396788341, ep_step: 1000 +2023-05-26 14:11:25 - SimpleLog - INFO: - episode: 1108, ep_reward: 796.5832791701976, ep_step: 1000 +2023-05-26 14:11:27 - SimpleLog - INFO: - episode: 1109, ep_reward: 595.5198317076922, ep_step: 1000 +2023-05-26 14:11:30 - SimpleLog - INFO: - episode: 1110, ep_reward: 519.7903269385763, ep_step: 1000 +2023-05-26 14:11:33 - SimpleLog - INFO: - episode: 1111, ep_reward: 943.8009332149513, ep_step: 1000 +2023-05-26 14:11:35 - SimpleLog - INFO: - episode: 1112, ep_reward: 401.5111152745373, ep_step: 1000 +2023-05-26 14:11:37 - SimpleLog - INFO: - episode: 1113, ep_reward: 605.1379347304046, ep_step: 1000 +2023-05-26 14:11:40 - SimpleLog - INFO: - episode: 1114, ep_reward: 562.3733307752723, ep_step: 1000 +2023-05-26 14:11:42 - SimpleLog - INFO: - episode: 1115, ep_reward: 487.6448805038168, ep_step: 1000 +2023-05-26 14:11:44 - SimpleLog - INFO: - episode: 1116, ep_reward: 387.1815713608556, ep_step: 1000 +2023-05-26 14:11:47 - SimpleLog - INFO: - episode: 1117, ep_reward: 685.7490206767069, ep_step: 1000 +2023-05-26 14:11:49 - SimpleLog - INFO: - episode: 1118, ep_reward: 489.70278116772545, ep_step: 1000 +2023-05-26 14:11:51 - SimpleLog - INFO: - episode: 1119, ep_reward: 481.127865804589, ep_step: 1000 +2023-05-26 14:11:53 - SimpleLog - INFO: - episode: 1120, ep_reward: 806.5338285165536, ep_step: 1000 +2023-05-26 14:11:56 - SimpleLog - INFO: - episode: 1121, ep_reward: 764.3918085831297, ep_step: 1000 +2023-05-26 14:11:58 - SimpleLog - INFO: - episode: 1122, ep_reward: 1169.3780290438071, ep_step: 1000 +2023-05-26 14:12:01 - SimpleLog - INFO: - episode: 1123, ep_reward: 367.91806739136524, ep_step: 1000 +2023-05-26 14:12:03 - SimpleLog - INFO: - episode: 1124, ep_reward: 556.4609973345327, ep_step: 1000 +2023-05-26 14:12:05 - SimpleLog - INFO: - episode: 1125, ep_reward: 644.795257767295, ep_step: 1000 +2023-05-26 14:12:06 - SimpleLog - INFO: - episode: 1126, ep_reward: 862.1239174153619, ep_step: 1000 +2023-05-26 14:12:08 - SimpleLog - INFO: - episode: 1127, ep_reward: 493.79130219803113, ep_step: 1000 +2023-05-26 14:12:10 - SimpleLog - INFO: - episode: 1128, ep_reward: 515.1424448677016, ep_step: 1000 +2023-05-26 14:12:12 - SimpleLog - INFO: - episode: 1129, ep_reward: 813.216617284676, ep_step: 1000 +2023-05-26 14:12:14 - SimpleLog - INFO: - episode: 1130, ep_reward: 446.0815517718721, ep_step: 1000 +2023-05-26 14:12:15 - SimpleLog - INFO: - episode: 1131, ep_reward: 275.0529292938654, ep_step: 1000 +2023-05-26 14:12:17 - SimpleLog - INFO: - episode: 1132, ep_reward: 542.2177188640445, ep_step: 1000 +2023-05-26 14:12:19 - SimpleLog - INFO: - episode: 1133, ep_reward: 591.6956358898526, ep_step: 1000 +2023-05-26 14:12:20 - SimpleLog - INFO: - episode: 1134, ep_reward: 399.87689141634854, ep_step: 1000 +2023-05-26 14:12:22 - SimpleLog - INFO: - episode: 1135, ep_reward: 582.8979126888861, ep_step: 1000 +2023-05-26 14:12:24 - SimpleLog - INFO: - episode: 1136, ep_reward: 415.70580539421337, ep_step: 1000 +2023-05-26 14:12:25 - SimpleLog - INFO: - episode: 1137, ep_reward: 587.4636263289312, ep_step: 1000 +2023-05-26 14:12:27 - SimpleLog - INFO: - episode: 1138, ep_reward: 652.1608256171022, ep_step: 1000 +2023-05-26 14:12:29 - SimpleLog - INFO: - episode: 1139, ep_reward: 332.28958194780205, ep_step: 1000 +2023-05-26 14:12:30 - SimpleLog - INFO: - episode: 1140, ep_reward: 364.6572842544124, ep_step: 1000 +2023-05-26 14:12:32 - SimpleLog - INFO: - episode: 1141, ep_reward: 446.5176522357124, ep_step: 1000 +2023-05-26 14:12:34 - SimpleLog - INFO: - episode: 1142, ep_reward: 608.4858756695673, ep_step: 1000 +2023-05-26 14:12:36 - SimpleLog - INFO: - episode: 1143, ep_reward: 671.9847753912932, ep_step: 1000 +2023-05-26 14:12:38 - SimpleLog - INFO: - episode: 1144, ep_reward: 341.86656175685334, ep_step: 1000 +2023-05-26 14:12:40 - SimpleLog - INFO: - episode: 1145, ep_reward: 472.0302461766135, ep_step: 1000 +2023-05-26 14:12:42 - SimpleLog - INFO: - episode: 1146, ep_reward: 384.3276695082272, ep_step: 1000 +2023-05-26 14:12:44 - SimpleLog - INFO: - episode: 1147, ep_reward: 572.944145997732, ep_step: 1000 +2023-05-26 14:12:45 - SimpleLog - INFO: - episode: 1148, ep_reward: 900.8407956475899, ep_step: 1000 +2023-05-26 14:12:47 - SimpleLog - INFO: - episode: 1149, ep_reward: 440.22500336172055, ep_step: 1000 +2023-05-26 14:12:49 - SimpleLog - INFO: - episode: 1150, ep_reward: 531.2575321935709, ep_step: 1000 +2023-05-26 14:12:56 - SimpleLog - INFO: - update_step: 4500, online_eval_reward: 482.262 +2023-05-26 14:12:56 - SimpleLog - INFO: - episode: 1151, ep_reward: 636.4553445992279, ep_step: 1000 +2023-05-26 14:12:57 - SimpleLog - INFO: - episode: 1152, ep_reward: 371.732427964515, ep_step: 1000 +2023-05-26 14:12:58 - SimpleLog - INFO: - episode: 1153, ep_reward: 310.60518010694915, ep_step: 1000 +2023-05-26 14:13:00 - SimpleLog - INFO: - episode: 1154, ep_reward: 568.6662090534759, ep_step: 1000 +2023-05-26 14:13:01 - SimpleLog - INFO: - episode: 1155, ep_reward: 449.9220287721516, ep_step: 1000 +2023-05-26 14:13:03 - SimpleLog - INFO: - episode: 1156, ep_reward: 429.7292851730472, ep_step: 1000 +2023-05-26 14:13:04 - SimpleLog - INFO: - episode: 1157, ep_reward: 592.0175095690846, ep_step: 1000 +2023-05-26 14:13:05 - SimpleLog - INFO: - episode: 1158, ep_reward: 271.3397622493485, ep_step: 1000 +2023-05-26 14:13:07 - SimpleLog - INFO: - episode: 1159, ep_reward: 700.3344364547154, ep_step: 1000 +2023-05-26 14:13:09 - SimpleLog - INFO: - episode: 1160, ep_reward: 416.6297510415938, ep_step: 1000 +2023-05-26 14:13:11 - SimpleLog - INFO: - episode: 1161, ep_reward: 348.7569289031999, ep_step: 1000 +2023-05-26 14:13:12 - SimpleLog - INFO: - episode: 1162, ep_reward: 366.58009126349236, ep_step: 1000 +2023-05-26 14:13:14 - SimpleLog - INFO: - episode: 1163, ep_reward: 736.4928884155157, ep_step: 1000 +2023-05-26 14:13:16 - SimpleLog - INFO: - episode: 1164, ep_reward: 430.89001777932873, ep_step: 1000 +2023-05-26 14:13:17 - SimpleLog - INFO: - episode: 1165, ep_reward: 1022.2831968079455, ep_step: 1000 +2023-05-26 14:13:19 - SimpleLog - INFO: - episode: 1166, ep_reward: 700.3316316101514, ep_step: 1000 +2023-05-26 14:13:21 - SimpleLog - INFO: - episode: 1167, ep_reward: 364.1391521377012, ep_step: 1000 +2023-05-26 14:13:22 - SimpleLog - INFO: - episode: 1168, ep_reward: 606.4965170851593, ep_step: 1000 +2023-05-26 14:13:24 - SimpleLog - INFO: - episode: 1169, ep_reward: 584.5761512365652, ep_step: 1000 +2023-05-26 14:13:26 - SimpleLog - INFO: - episode: 1170, ep_reward: 552.3215545350039, ep_step: 1000 +2023-05-26 14:13:28 - SimpleLog - INFO: - episode: 1171, ep_reward: 1225.2562888958075, ep_step: 1000 +2023-05-26 14:13:29 - SimpleLog - INFO: - episode: 1172, ep_reward: 481.0898508267982, ep_step: 1000 +2023-05-26 14:13:31 - SimpleLog - INFO: - episode: 1173, ep_reward: 284.0571225369636, ep_step: 1000 +2023-05-26 14:13:33 - SimpleLog - INFO: - episode: 1174, ep_reward: 872.9969060245334, ep_step: 1000 +2023-05-26 14:13:34 - SimpleLog - INFO: - episode: 1175, ep_reward: 305.9701769579424, ep_step: 1000 +2023-05-26 14:13:36 - SimpleLog - INFO: - episode: 1176, ep_reward: 692.1289223439401, ep_step: 1000 +2023-05-26 14:13:38 - SimpleLog - INFO: - episode: 1177, ep_reward: 997.2618774532885, ep_step: 1000 +2023-05-26 14:13:40 - SimpleLog - INFO: - episode: 1178, ep_reward: 609.2367706393932, ep_step: 1000 +2023-05-26 14:13:42 - SimpleLog - INFO: - episode: 1179, ep_reward: 416.7278263701349, ep_step: 1000 +2023-05-26 14:13:44 - SimpleLog - INFO: - episode: 1180, ep_reward: 719.2412838982094, ep_step: 1000 +2023-05-26 14:13:46 - SimpleLog - INFO: - episode: 1181, ep_reward: 1172.169143769351, ep_step: 1000 +2023-05-26 14:13:48 - SimpleLog - INFO: - episode: 1182, ep_reward: 499.8546489329396, ep_step: 1000 +2023-05-26 14:13:50 - SimpleLog - INFO: - episode: 1183, ep_reward: 472.0234148434372, ep_step: 1000 +2023-05-26 14:13:51 - SimpleLog - INFO: - episode: 1184, ep_reward: 414.9722625873827, ep_step: 1000 +2023-05-26 14:13:53 - SimpleLog - INFO: - episode: 1185, ep_reward: 883.0243859758004, ep_step: 1000 +2023-05-26 14:13:55 - SimpleLog - INFO: - episode: 1186, ep_reward: 436.81796784983607, ep_step: 1000 +2023-05-26 14:13:57 - SimpleLog - INFO: - episode: 1187, ep_reward: 469.51943670127986, ep_step: 1000 +2023-05-26 14:13:59 - SimpleLog - INFO: - episode: 1188, ep_reward: 517.2237013987226, ep_step: 1000 +2023-05-26 14:14:00 - SimpleLog - INFO: - episode: 1189, ep_reward: 763.8619905373248, ep_step: 1000 +2023-05-26 14:14:02 - SimpleLog - INFO: - episode: 1190, ep_reward: 288.558214745043, ep_step: 1000 +2023-05-26 14:14:04 - SimpleLog - INFO: - episode: 1191, ep_reward: 561.906984193027, ep_step: 1000 +2023-05-26 14:14:06 - SimpleLog - INFO: - episode: 1192, ep_reward: 689.3183563595051, ep_step: 1000 +2023-05-26 14:14:08 - SimpleLog - INFO: - episode: 1193, ep_reward: 762.9290455252708, ep_step: 1000 +2023-05-26 14:14:09 - SimpleLog - INFO: - episode: 1194, ep_reward: 556.0997532084912, ep_step: 1000 +2023-05-26 14:14:11 - SimpleLog - INFO: - episode: 1195, ep_reward: 808.399175265781, ep_step: 1000 +2023-05-26 14:14:13 - SimpleLog - INFO: - episode: 1196, ep_reward: 232.41357185185825, ep_step: 1000 +2023-05-26 14:14:15 - SimpleLog - INFO: - episode: 1197, ep_reward: 841.713335740815, ep_step: 1000 +2023-05-26 14:14:16 - SimpleLog - INFO: - episode: 1198, ep_reward: 529.3659218304085, ep_step: 1000 +2023-05-26 14:14:18 - SimpleLog - INFO: - episode: 1199, ep_reward: 255.77947946020822, ep_step: 1000 +2023-05-26 14:14:20 - SimpleLog - INFO: - episode: 1200, ep_reward: 488.37672790537954, ep_step: 1000 +2023-05-26 14:14:22 - SimpleLog - INFO: - episode: 1201, ep_reward: 637.1603021374152, ep_step: 1000 +2023-05-26 14:14:23 - SimpleLog - INFO: - episode: 1202, ep_reward: 1072.7598808712723, ep_step: 1000 +2023-05-26 14:14:25 - SimpleLog - INFO: - episode: 1203, ep_reward: 804.8420602400683, ep_step: 1000 +2023-05-26 14:14:27 - SimpleLog - INFO: - episode: 1204, ep_reward: 354.632803510605, ep_step: 1000 +2023-05-26 14:14:29 - SimpleLog - INFO: - episode: 1205, ep_reward: 378.9850933292031, ep_step: 1000 +2023-05-26 14:14:30 - SimpleLog - INFO: - episode: 1206, ep_reward: 758.1489718502334, ep_step: 1000 +2023-05-26 14:14:32 - SimpleLog - INFO: - episode: 1207, ep_reward: 418.7305386166752, ep_step: 1000 +2023-05-26 14:14:34 - SimpleLog - INFO: - episode: 1208, ep_reward: 727.902352638586, ep_step: 1000 +2023-05-26 14:14:35 - SimpleLog - INFO: - episode: 1209, ep_reward: 442.4391927165751, ep_step: 1000 +2023-05-26 14:14:37 - SimpleLog - INFO: - episode: 1210, ep_reward: 471.7574681063461, ep_step: 1000 +2023-05-26 14:14:39 - SimpleLog - INFO: - episode: 1211, ep_reward: 702.7470615102703, ep_step: 1000 +2023-05-26 14:14:40 - SimpleLog - INFO: - episode: 1212, ep_reward: 961.3301531296562, ep_step: 1000 +2023-05-26 14:14:42 - SimpleLog - INFO: - episode: 1213, ep_reward: 693.4428273276826, ep_step: 1000 +2023-05-26 14:14:44 - SimpleLog - INFO: - episode: 1214, ep_reward: 399.65978845585363, ep_step: 1000 +2023-05-26 14:14:46 - SimpleLog - INFO: - episode: 1215, ep_reward: 883.1775774912836, ep_step: 1000 +2023-05-26 14:14:47 - SimpleLog - INFO: - episode: 1216, ep_reward: 491.9007929733613, ep_step: 1000 +2023-05-26 14:14:49 - SimpleLog - INFO: - episode: 1217, ep_reward: 409.4037324807582, ep_step: 1000 +2023-05-26 14:14:52 - SimpleLog - INFO: - episode: 1218, ep_reward: 232.8275702871743, ep_step: 1000 +2023-05-26 14:14:54 - SimpleLog - INFO: - episode: 1219, ep_reward: 430.54641364609455, ep_step: 1000 +2023-05-26 14:14:55 - SimpleLog - INFO: - episode: 1220, ep_reward: 615.6100258365523, ep_step: 1000 +2023-05-26 14:14:57 - SimpleLog - INFO: - episode: 1221, ep_reward: 726.402584489642, ep_step: 1000 +2023-05-26 14:14:59 - SimpleLog - INFO: - episode: 1222, ep_reward: 780.4180826221487, ep_step: 1000 +2023-05-26 14:15:00 - SimpleLog - INFO: - episode: 1223, ep_reward: 682.8532786247039, ep_step: 1000 +2023-05-26 14:15:02 - SimpleLog - INFO: - episode: 1224, ep_reward: 726.4864923237685, ep_step: 1000 +2023-05-26 14:15:04 - SimpleLog - INFO: - episode: 1225, ep_reward: 947.6497700898376, ep_step: 1000 +2023-05-26 14:15:05 - SimpleLog - INFO: - episode: 1226, ep_reward: 665.7591306971356, ep_step: 1000 +2023-05-26 14:15:07 - SimpleLog - INFO: - episode: 1227, ep_reward: 374.44000455850824, ep_step: 1000 +2023-05-26 14:15:09 - SimpleLog - INFO: - episode: 1228, ep_reward: 528.6339329805254, ep_step: 1000 +2023-05-26 14:15:10 - SimpleLog - INFO: - episode: 1229, ep_reward: 1003.3194180777379, ep_step: 1000 +2023-05-26 14:15:12 - SimpleLog - INFO: - episode: 1230, ep_reward: 949.4992049211294, ep_step: 1000 +2023-05-26 14:15:14 - SimpleLog - INFO: - episode: 1231, ep_reward: 958.4261257900727, ep_step: 1000 +2023-05-26 14:15:16 - SimpleLog - INFO: - episode: 1232, ep_reward: 845.6925416179995, ep_step: 1000 +2023-05-26 14:15:17 - SimpleLog - INFO: - episode: 1233, ep_reward: 920.1421652317534, ep_step: 1000 +2023-05-26 14:15:19 - SimpleLog - INFO: - episode: 1234, ep_reward: 497.48042118547465, ep_step: 1000 +2023-05-26 14:15:21 - SimpleLog - INFO: - episode: 1235, ep_reward: 570.565929091362, ep_step: 1000 +2023-05-26 14:15:23 - SimpleLog - INFO: - episode: 1236, ep_reward: 452.1166394873371, ep_step: 1000 +2023-05-26 14:15:24 - SimpleLog - INFO: - episode: 1237, ep_reward: 954.5616053230441, ep_step: 1000 +2023-05-26 14:15:26 - SimpleLog - INFO: - episode: 1238, ep_reward: 980.2287447110638, ep_step: 1000 +2023-05-26 14:15:28 - SimpleLog - INFO: - episode: 1239, ep_reward: 862.6652813927486, ep_step: 1000 +2023-05-26 14:15:29 - SimpleLog - INFO: - episode: 1240, ep_reward: 362.3858319223656, ep_step: 1000 +2023-05-26 14:15:31 - SimpleLog - INFO: - episode: 1241, ep_reward: 923.6683469721204, ep_step: 1000 +2023-05-26 14:15:33 - SimpleLog - INFO: - episode: 1242, ep_reward: 517.9747140683162, ep_step: 1000 +2023-05-26 14:15:34 - SimpleLog - INFO: - episode: 1243, ep_reward: 500.7692253068478, ep_step: 1000 +2023-05-26 14:15:36 - SimpleLog - INFO: - episode: 1244, ep_reward: 612.0485255396228, ep_step: 1000 +2023-05-26 14:15:38 - SimpleLog - INFO: - episode: 1245, ep_reward: 833.9888795984396, ep_step: 1000 +2023-05-26 14:15:40 - SimpleLog - INFO: - episode: 1246, ep_reward: 779.3821686701701, ep_step: 1000 +2023-05-26 14:15:42 - SimpleLog - INFO: - episode: 1247, ep_reward: 436.50757150015835, ep_step: 1000 +2023-05-26 14:15:43 - SimpleLog - INFO: - episode: 1248, ep_reward: 1117.002454933344, ep_step: 1000 +2023-05-26 14:15:45 - SimpleLog - INFO: - episode: 1249, ep_reward: 830.8097005863317, ep_step: 1000 +2023-05-26 14:15:46 - SimpleLog - INFO: - episode: 1250, ep_reward: 534.022569212704, ep_step: 1000 +2023-05-26 14:15:48 - SimpleLog - INFO: - episode: 1251, ep_reward: 456.47199683333133, ep_step: 1000 +2023-05-26 14:15:50 - SimpleLog - INFO: - episode: 1252, ep_reward: 876.848717777719, ep_step: 1000 +2023-05-26 14:15:52 - SimpleLog - INFO: - episode: 1253, ep_reward: 736.7747945211844, ep_step: 1000 +2023-05-26 14:15:54 - SimpleLog - INFO: - episode: 1254, ep_reward: 438.95601525287486, ep_step: 1000 +2023-05-26 14:15:56 - SimpleLog - INFO: - episode: 1255, ep_reward: 462.5048378954506, ep_step: 1000 +2023-05-26 14:15:58 - SimpleLog - INFO: - episode: 1256, ep_reward: 855.7643798241262, ep_step: 1000 +2023-05-26 14:16:00 - SimpleLog - INFO: - episode: 1257, ep_reward: 628.8648343729571, ep_step: 1000 +2023-05-26 14:16:01 - SimpleLog - INFO: - episode: 1258, ep_reward: 753.5924493363159, ep_step: 1000 +2023-05-26 14:16:03 - SimpleLog - INFO: - episode: 1259, ep_reward: 848.8517988779546, ep_step: 1000 +2023-05-26 14:16:05 - SimpleLog - INFO: - episode: 1260, ep_reward: 954.5103650164295, ep_step: 1000 +2023-05-26 14:16:07 - SimpleLog - INFO: - episode: 1261, ep_reward: 1066.459940237471, ep_step: 1000 +2023-05-26 14:16:08 - SimpleLog - INFO: - episode: 1262, ep_reward: 493.78527850108446, ep_step: 1000 +2023-05-26 14:16:10 - SimpleLog - INFO: - episode: 1263, ep_reward: 348.24710999827903, ep_step: 1000 +2023-05-26 14:16:12 - SimpleLog - INFO: - episode: 1264, ep_reward: 385.9357418746537, ep_step: 1000 +2023-05-26 14:16:14 - SimpleLog - INFO: - episode: 1265, ep_reward: 589.2489834116135, ep_step: 1000 +2023-05-26 14:16:15 - SimpleLog - INFO: - episode: 1266, ep_reward: 1032.376416906939, ep_step: 1000 +2023-05-26 14:16:17 - SimpleLog - INFO: - episode: 1267, ep_reward: 409.4049506924234, ep_step: 1000 +2023-05-26 14:16:19 - SimpleLog - INFO: - episode: 1268, ep_reward: 285.102850348328, ep_step: 1000 +2023-05-26 14:16:20 - SimpleLog - INFO: - episode: 1269, ep_reward: 807.3229559185987, ep_step: 1000 +2023-05-26 14:16:22 - SimpleLog - INFO: - episode: 1270, ep_reward: 917.6894022881544, ep_step: 1000 +2023-05-26 14:16:24 - SimpleLog - INFO: - episode: 1271, ep_reward: 344.56792022131094, ep_step: 1000 +2023-05-26 14:16:26 - SimpleLog - INFO: - episode: 1272, ep_reward: 1024.7527164445817, ep_step: 1000 +2023-05-26 14:16:27 - SimpleLog - INFO: - episode: 1273, ep_reward: 463.1308834486718, ep_step: 1000 +2023-05-26 14:16:29 - SimpleLog - INFO: - episode: 1274, ep_reward: 982.0974970764539, ep_step: 1000 +2023-05-26 14:16:31 - SimpleLog - INFO: - episode: 1275, ep_reward: 405.53055411393876, ep_step: 1000 +2023-05-26 14:16:33 - SimpleLog - INFO: - episode: 1276, ep_reward: 997.5329856636226, ep_step: 1000 +2023-05-26 14:16:34 - SimpleLog - INFO: - episode: 1277, ep_reward: 439.30999760428546, ep_step: 1000 +2023-05-26 14:16:36 - SimpleLog - INFO: - episode: 1278, ep_reward: 751.1330145193584, ep_step: 1000 +2023-05-26 14:16:43 - SimpleLog - INFO: - update_step: 5000, online_eval_reward: 260.176 +2023-05-26 14:16:43 - SimpleLog - INFO: - episode: 1279, ep_reward: 698.2284741507498, ep_step: 1000 +2023-05-26 14:16:44 - SimpleLog - INFO: - episode: 1280, ep_reward: 602.0000901687256, ep_step: 1000 +2023-05-26 14:16:46 - SimpleLog - INFO: - episode: 1281, ep_reward: 850.2408020752008, ep_step: 1000 +2023-05-26 14:16:47 - SimpleLog - INFO: - episode: 1282, ep_reward: 744.0140655028434, ep_step: 1000 +2023-05-26 14:16:48 - SimpleLog - INFO: - episode: 1283, ep_reward: 480.7341242732814, ep_step: 1000 +2023-05-26 14:16:49 - SimpleLog - INFO: - episode: 1284, ep_reward: 621.2139084277042, ep_step: 1000 +2023-05-26 14:16:51 - SimpleLog - INFO: - episode: 1285, ep_reward: 896.8482681719993, ep_step: 1000 +2023-05-26 14:16:52 - SimpleLog - INFO: - episode: 1286, ep_reward: 334.9430658527852, ep_step: 1000 +2023-05-26 14:16:53 - SimpleLog - INFO: - episode: 1287, ep_reward: 470.76781819594225, ep_step: 1000 +2023-05-26 14:16:54 - SimpleLog - INFO: - episode: 1288, ep_reward: 405.91604525564225, ep_step: 1000 +2023-05-26 14:16:56 - SimpleLog - INFO: - episode: 1289, ep_reward: 703.3193291125908, ep_step: 1000 +2023-05-26 14:16:57 - SimpleLog - INFO: - episode: 1290, ep_reward: 998.1442188904103, ep_step: 1000 +2023-05-26 14:16:58 - SimpleLog - INFO: - episode: 1291, ep_reward: 324.3493555161426, ep_step: 1000 +2023-05-26 14:16:59 - SimpleLog - INFO: - episode: 1292, ep_reward: 549.5360842540224, ep_step: 1000 +2023-05-26 14:17:01 - SimpleLog - INFO: - episode: 1293, ep_reward: 396.8148501555896, ep_step: 1000 +2023-05-26 14:17:03 - SimpleLog - INFO: - episode: 1294, ep_reward: 524.7204719691262, ep_step: 1000 +2023-05-26 14:17:05 - SimpleLog - INFO: - episode: 1295, ep_reward: 944.5212076370128, ep_step: 1000 +2023-05-26 14:17:07 - SimpleLog - INFO: - episode: 1296, ep_reward: 953.757662221333, ep_step: 1000 +2023-05-26 14:17:08 - SimpleLog - INFO: - episode: 1297, ep_reward: 478.1265784950697, ep_step: 1000 +2023-05-26 14:17:10 - SimpleLog - INFO: - episode: 1298, ep_reward: 428.24066966016755, ep_step: 1000 +2023-05-26 14:17:12 - SimpleLog - INFO: - episode: 1299, ep_reward: 1113.7474990789144, ep_step: 1000 +2023-05-26 14:17:13 - SimpleLog - INFO: - episode: 1300, ep_reward: 537.5550713775328, ep_step: 1000 +2023-05-26 14:17:15 - SimpleLog - INFO: - episode: 1301, ep_reward: 541.7541850165272, ep_step: 1000 +2023-05-26 14:17:17 - SimpleLog - INFO: - episode: 1302, ep_reward: 469.20332652151114, ep_step: 1000 +2023-05-26 14:17:19 - SimpleLog - INFO: - episode: 1303, ep_reward: 796.0942261544175, ep_step: 1000 +2023-05-26 14:17:21 - SimpleLog - INFO: - episode: 1304, ep_reward: 494.60313361719284, ep_step: 1000 +2023-05-26 14:17:22 - SimpleLog - INFO: - episode: 1305, ep_reward: 941.138999509193, ep_step: 1000 +2023-05-26 14:17:24 - SimpleLog - INFO: - episode: 1306, ep_reward: 766.6920922597017, ep_step: 1000 +2023-05-26 14:17:26 - SimpleLog - INFO: - episode: 1307, ep_reward: 1004.5200254506647, ep_step: 1000 +2023-05-26 14:17:27 - SimpleLog - INFO: - episode: 1308, ep_reward: 499.00895927832465, ep_step: 1000 +2023-05-26 14:17:29 - SimpleLog - INFO: - episode: 1309, ep_reward: 568.6858401536584, ep_step: 1000 +2023-05-26 14:17:31 - SimpleLog - INFO: - episode: 1310, ep_reward: 850.7308557841327, ep_step: 1000 +2023-05-26 14:17:33 - SimpleLog - INFO: - episode: 1311, ep_reward: 500.8987789509806, ep_step: 1000 +2023-05-26 14:17:35 - SimpleLog - INFO: - episode: 1312, ep_reward: 599.2182627490228, ep_step: 1000 +2023-05-26 14:17:36 - SimpleLog - INFO: - episode: 1313, ep_reward: 840.7738039060957, ep_step: 1000 +2023-05-26 14:17:38 - SimpleLog - INFO: - episode: 1314, ep_reward: 967.27015684887, ep_step: 1000 +2023-05-26 14:17:40 - SimpleLog - INFO: - episode: 1315, ep_reward: 683.7172288657991, ep_step: 1000 +2023-05-26 14:17:41 - SimpleLog - INFO: - episode: 1316, ep_reward: 719.4415514702936, ep_step: 1000 +2023-05-26 14:17:43 - SimpleLog - INFO: - episode: 1317, ep_reward: 707.3104843062803, ep_step: 1000 +2023-05-26 14:17:45 - SimpleLog - INFO: - episode: 1318, ep_reward: 422.8012678781682, ep_step: 1000 +2023-05-26 14:17:46 - SimpleLog - INFO: - episode: 1319, ep_reward: 368.1485125321898, ep_step: 1000 +2023-05-26 14:17:48 - SimpleLog - INFO: - episode: 1320, ep_reward: 295.95036139386843, ep_step: 1000 +2023-05-26 14:17:50 - SimpleLog - INFO: - episode: 1321, ep_reward: 971.6608990636373, ep_step: 1000 +2023-05-26 14:17:51 - SimpleLog - INFO: - episode: 1322, ep_reward: 541.1362207079508, ep_step: 1000 +2023-05-26 14:17:53 - SimpleLog - INFO: - episode: 1323, ep_reward: 980.6361547271176, ep_step: 1000 +2023-05-26 14:17:55 - SimpleLog - INFO: - episode: 1324, ep_reward: 312.98064105151997, ep_step: 1000 +2023-05-26 14:17:56 - SimpleLog - INFO: - episode: 1325, ep_reward: 555.6961735075319, ep_step: 1000 +2023-05-26 14:17:58 - SimpleLog - INFO: - episode: 1326, ep_reward: 840.9389962222035, ep_step: 1000 +2023-05-26 14:18:00 - SimpleLog - INFO: - episode: 1327, ep_reward: 668.4222197905001, ep_step: 1000 +2023-05-26 14:18:02 - SimpleLog - INFO: - episode: 1328, ep_reward: 647.9361444316437, ep_step: 1000 +2023-05-26 14:18:03 - SimpleLog - INFO: - episode: 1329, ep_reward: 647.5537387828283, ep_step: 1000 +2023-05-26 14:18:05 - SimpleLog - INFO: - episode: 1330, ep_reward: 1088.8886658708693, ep_step: 1000 +2023-05-26 14:18:07 - SimpleLog - INFO: - episode: 1331, ep_reward: 655.896680387653, ep_step: 1000 +2023-05-26 14:18:09 - SimpleLog - INFO: - episode: 1332, ep_reward: 973.5347816623628, ep_step: 1000 +2023-05-26 14:18:11 - SimpleLog - INFO: - episode: 1333, ep_reward: 864.4945121138398, ep_step: 1000 +2023-05-26 14:18:13 - SimpleLog - INFO: - episode: 1334, ep_reward: 502.0477574542, ep_step: 1000 +2023-05-26 14:18:15 - SimpleLog - INFO: - episode: 1335, ep_reward: 380.735539352138, ep_step: 1000 +2023-05-26 14:18:16 - SimpleLog - INFO: - episode: 1336, ep_reward: 442.4133668696393, ep_step: 1000 +2023-05-26 14:18:18 - SimpleLog - INFO: - episode: 1337, ep_reward: 505.5680140554597, ep_step: 1000 +2023-05-26 14:18:20 - SimpleLog - INFO: - episode: 1338, ep_reward: 720.395701569416, ep_step: 1000 +2023-05-26 14:18:22 - SimpleLog - INFO: - episode: 1339, ep_reward: 780.2995023788234, ep_step: 1000 +2023-05-26 14:18:23 - SimpleLog - INFO: - episode: 1340, ep_reward: 521.4530090093613, ep_step: 1000 +2023-05-26 14:18:25 - SimpleLog - INFO: - episode: 1341, ep_reward: 596.6569260338781, ep_step: 1000 +2023-05-26 14:18:27 - SimpleLog - INFO: - episode: 1342, ep_reward: 654.6814856156641, ep_step: 1000 +2023-05-26 14:18:29 - SimpleLog - INFO: - episode: 1343, ep_reward: 1119.2694285334528, ep_step: 1000 +2023-05-26 14:18:30 - SimpleLog - INFO: - episode: 1344, ep_reward: 399.76623339003163, ep_step: 1000 +2023-05-26 14:18:32 - SimpleLog - INFO: - episode: 1345, ep_reward: 576.2342979212024, ep_step: 1000 +2023-05-26 14:18:34 - SimpleLog - INFO: - episode: 1346, ep_reward: 273.0233745130537, ep_step: 1000 +2023-05-26 14:18:35 - SimpleLog - INFO: - episode: 1347, ep_reward: 509.45508825521415, ep_step: 1000 +2023-05-26 14:18:37 - SimpleLog - INFO: - episode: 1348, ep_reward: 491.86183085911034, ep_step: 1000 +2023-05-26 14:18:39 - SimpleLog - INFO: - episode: 1349, ep_reward: 970.4507052011522, ep_step: 1000 +2023-05-26 14:18:40 - SimpleLog - INFO: - episode: 1350, ep_reward: 730.0266943062135, ep_step: 1000 +2023-05-26 14:18:42 - SimpleLog - INFO: - episode: 1351, ep_reward: 548.6555401832858, ep_step: 1000 +2023-05-26 14:18:44 - SimpleLog - INFO: - episode: 1352, ep_reward: 147.82113170308247, ep_step: 1000 +2023-05-26 14:18:45 - SimpleLog - INFO: - episode: 1353, ep_reward: 774.9380833041954, ep_step: 1000 +2023-05-26 14:18:47 - SimpleLog - INFO: - episode: 1354, ep_reward: 311.3551996287938, ep_step: 1000 +2023-05-26 14:18:49 - SimpleLog - INFO: - episode: 1355, ep_reward: 162.348693656412, ep_step: 1000 +2023-05-26 14:18:51 - SimpleLog - INFO: - episode: 1356, ep_reward: 690.8664676769129, ep_step: 1000 +2023-05-26 14:18:52 - SimpleLog - INFO: - episode: 1357, ep_reward: 620.1574568362673, ep_step: 1000 +2023-05-26 14:18:54 - SimpleLog - INFO: - episode: 1358, ep_reward: 839.491306650301, ep_step: 1000 +2023-05-26 14:18:56 - SimpleLog - INFO: - episode: 1359, ep_reward: 377.35340886154364, ep_step: 1000 +2023-05-26 14:18:57 - SimpleLog - INFO: - episode: 1360, ep_reward: 191.866006300468, ep_step: 1000 +2023-05-26 14:18:59 - SimpleLog - INFO: - episode: 1361, ep_reward: 667.4241048087762, ep_step: 1000 +2023-05-26 14:19:01 - SimpleLog - INFO: - episode: 1362, ep_reward: 1037.8378691881646, ep_step: 1000 +2023-05-26 14:19:02 - SimpleLog - INFO: - episode: 1363, ep_reward: 806.7763199912673, ep_step: 1000 +2023-05-26 14:19:04 - SimpleLog - INFO: - episode: 1364, ep_reward: 797.2186180217597, ep_step: 1000 +2023-05-26 14:19:06 - SimpleLog - INFO: - episode: 1365, ep_reward: 362.73778930440017, ep_step: 1000 +2023-05-26 14:19:07 - SimpleLog - INFO: - episode: 1366, ep_reward: 792.9909362712559, ep_step: 1000 +2023-05-26 14:19:09 - SimpleLog - INFO: - episode: 1367, ep_reward: 779.7911172305842, ep_step: 1000 +2023-05-26 14:19:11 - SimpleLog - INFO: - episode: 1368, ep_reward: 809.9459133891611, ep_step: 1000 +2023-05-26 14:19:12 - SimpleLog - INFO: - episode: 1369, ep_reward: 934.1452881778903, ep_step: 1000 +2023-05-26 14:19:14 - SimpleLog - INFO: - episode: 1370, ep_reward: 706.4009611563005, ep_step: 1000 +2023-05-26 14:19:17 - SimpleLog - INFO: - episode: 1371, ep_reward: 685.8084428105801, ep_step: 1000 +2023-05-26 14:19:19 - SimpleLog - INFO: - episode: 1372, ep_reward: 628.0745983250861, ep_step: 1000 +2023-05-26 14:19:21 - SimpleLog - INFO: - episode: 1373, ep_reward: 186.2476614602444, ep_step: 1000 +2023-05-26 14:19:22 - SimpleLog - INFO: - episode: 1374, ep_reward: 553.6537109502431, ep_step: 1000 +2023-05-26 14:19:24 - SimpleLog - INFO: - episode: 1375, ep_reward: 1206.2631637553584, ep_step: 1000 +2023-05-26 14:19:26 - SimpleLog - INFO: - episode: 1376, ep_reward: 471.18880493894306, ep_step: 1000 +2023-05-26 14:19:27 - SimpleLog - INFO: - episode: 1377, ep_reward: 401.22374314848173, ep_step: 1000 +2023-05-26 14:19:29 - SimpleLog - INFO: - episode: 1378, ep_reward: 307.94637651187793, ep_step: 1000 +2023-05-26 14:19:31 - SimpleLog - INFO: - episode: 1379, ep_reward: 465.1019913131932, ep_step: 1000 +2023-05-26 14:19:33 - SimpleLog - INFO: - episode: 1380, ep_reward: 634.6265974855266, ep_step: 1000 +2023-05-26 14:19:35 - SimpleLog - INFO: - episode: 1381, ep_reward: 204.6089884902781, ep_step: 1000 +2023-05-26 14:19:37 - SimpleLog - INFO: - episode: 1382, ep_reward: 329.65595186368216, ep_step: 1000 +2023-05-26 14:19:38 - SimpleLog - INFO: - episode: 1383, ep_reward: 201.5601791728325, ep_step: 1000 +2023-05-26 14:19:40 - SimpleLog - INFO: - episode: 1384, ep_reward: 867.2103568638333, ep_step: 1000 +2023-05-26 14:19:42 - SimpleLog - INFO: - episode: 1385, ep_reward: 444.56426480281345, ep_step: 1000 +2023-05-26 14:19:43 - SimpleLog - INFO: - episode: 1386, ep_reward: 692.1484471463941, ep_step: 1000 +2023-05-26 14:19:45 - SimpleLog - INFO: - episode: 1387, ep_reward: 778.255041869653, ep_step: 1000 +2023-05-26 14:19:47 - SimpleLog - INFO: - episode: 1388, ep_reward: 648.5398818234462, ep_step: 1000 +2023-05-26 14:19:49 - SimpleLog - INFO: - episode: 1389, ep_reward: 435.44887314811285, ep_step: 1000 +2023-05-26 14:19:50 - SimpleLog - INFO: - episode: 1390, ep_reward: 584.546459640308, ep_step: 1000 +2023-05-26 14:19:52 - SimpleLog - INFO: - episode: 1391, ep_reward: 743.6097514834619, ep_step: 1000 +2023-05-26 14:19:54 - SimpleLog - INFO: - episode: 1392, ep_reward: 62.20594249027998, ep_step: 1000 +2023-05-26 14:19:56 - SimpleLog - INFO: - episode: 1393, ep_reward: 380.4924658144654, ep_step: 1000 +2023-05-26 14:19:57 - SimpleLog - INFO: - episode: 1394, ep_reward: 525.1628341154162, ep_step: 1000 +2023-05-26 14:19:59 - SimpleLog - INFO: - episode: 1395, ep_reward: 246.38983992593143, ep_step: 1000 +2023-05-26 14:20:01 - SimpleLog - INFO: - episode: 1396, ep_reward: 368.7417017520801, ep_step: 1000 +2023-05-26 14:20:02 - SimpleLog - INFO: - episode: 1397, ep_reward: 66.729341739029, ep_step: 1000 +2023-05-26 14:20:04 - SimpleLog - INFO: - episode: 1398, ep_reward: 392.56548562218006, ep_step: 1000 +2023-05-26 14:20:06 - SimpleLog - INFO: - episode: 1399, ep_reward: 458.00759219101093, ep_step: 1000 +2023-05-26 14:20:07 - SimpleLog - INFO: - episode: 1400, ep_reward: 588.6189114906756, ep_step: 1000 +2023-05-26 14:20:09 - SimpleLog - INFO: - episode: 1401, ep_reward: 407.26025604933903, ep_step: 1000 +2023-05-26 14:20:11 - SimpleLog - INFO: - episode: 1402, ep_reward: 629.1610044099581, ep_step: 1000 +2023-05-26 14:20:13 - SimpleLog - INFO: - episode: 1403, ep_reward: 580.9660972626974, ep_step: 1000 +2023-05-26 14:20:14 - SimpleLog - INFO: - episode: 1404, ep_reward: 794.6687511578534, ep_step: 1000 +2023-05-26 14:20:16 - SimpleLog - INFO: - episode: 1405, ep_reward: 602.791814430091, ep_step: 1000 +2023-05-26 14:20:18 - SimpleLog - INFO: - episode: 1406, ep_reward: 409.6095612389829, ep_step: 1000 +2023-05-26 14:20:25 - SimpleLog - INFO: - update_step: 5500, online_eval_reward: 803.797 +2023-05-26 14:20:25 - SimpleLog - INFO: - episode: 1407, ep_reward: 344.1045007735151, ep_step: 1000 +2023-05-26 14:20:26 - SimpleLog - INFO: - episode: 1408, ep_reward: 402.689919758883, ep_step: 1000 +2023-05-26 14:20:28 - SimpleLog - INFO: - episode: 1409, ep_reward: 482.55241426819964, ep_step: 1000 +2023-05-26 14:20:29 - SimpleLog - INFO: - episode: 1410, ep_reward: 227.5465470384412, ep_step: 1000 +2023-05-26 14:20:30 - SimpleLog - INFO: - episode: 1411, ep_reward: 331.9881392021876, ep_step: 1000 +2023-05-26 14:20:32 - SimpleLog - INFO: - episode: 1412, ep_reward: 849.5339215530223, ep_step: 1000 +2023-05-26 14:20:34 - SimpleLog - INFO: - episode: 1413, ep_reward: 326.1072710417352, ep_step: 1000 +2023-05-26 14:20:35 - SimpleLog - INFO: - episode: 1414, ep_reward: 490.12251915157657, ep_step: 1000 +2023-05-26 14:20:37 - SimpleLog - INFO: - episode: 1415, ep_reward: 788.8245908579974, ep_step: 1000 +2023-05-26 14:20:39 - SimpleLog - INFO: - episode: 1416, ep_reward: 386.5051342649371, ep_step: 1000 +2023-05-26 14:20:41 - SimpleLog - INFO: - episode: 1417, ep_reward: 616.1769147530136, ep_step: 1000 +2023-05-26 14:20:42 - SimpleLog - INFO: - episode: 1418, ep_reward: 475.46575966232126, ep_step: 1000 +2023-05-26 14:20:44 - SimpleLog - INFO: - episode: 1419, ep_reward: 376.58318488228184, ep_step: 1000 +2023-05-26 14:20:46 - SimpleLog - INFO: - episode: 1420, ep_reward: 593.7311201013567, ep_step: 1000 +2023-05-26 14:20:48 - SimpleLog - INFO: - episode: 1421, ep_reward: 872.5888708432989, ep_step: 1000 +2023-05-26 14:20:49 - SimpleLog - INFO: - episode: 1422, ep_reward: 744.7976443830767, ep_step: 1000 +2023-05-26 14:20:51 - SimpleLog - INFO: - episode: 1423, ep_reward: 460.4057614166176, ep_step: 1000 +2023-05-26 14:20:53 - SimpleLog - INFO: - episode: 1424, ep_reward: 323.0258334233924, ep_step: 1000 +2023-05-26 14:20:55 - SimpleLog - INFO: - episode: 1425, ep_reward: 360.66319200521815, ep_step: 1000 +2023-05-26 14:20:56 - SimpleLog - INFO: - episode: 1426, ep_reward: 265.8539055343251, ep_step: 1000 +2023-05-26 14:20:58 - SimpleLog - INFO: - episode: 1427, ep_reward: 487.3642055720868, ep_step: 1000 +2023-05-26 14:21:00 - SimpleLog - INFO: - episode: 1428, ep_reward: 651.5733169915246, ep_step: 1000 +2023-05-26 14:21:01 - SimpleLog - INFO: - episode: 1429, ep_reward: 428.4825944601509, ep_step: 1000 +2023-05-26 14:21:03 - SimpleLog - INFO: - episode: 1430, ep_reward: 137.34262181545782, ep_step: 1000 +2023-05-26 14:21:05 - SimpleLog - INFO: - episode: 1431, ep_reward: 284.94451657969705, ep_step: 1000 +2023-05-26 14:21:06 - SimpleLog - INFO: - episode: 1432, ep_reward: 447.4253054432217, ep_step: 1000 +2023-05-26 14:21:08 - SimpleLog - INFO: - episode: 1433, ep_reward: 746.5213620729609, ep_step: 1000 +2023-05-26 14:21:10 - SimpleLog - INFO: - episode: 1434, ep_reward: 242.68363942194196, ep_step: 1000 +2023-05-26 14:21:11 - SimpleLog - INFO: - episode: 1435, ep_reward: 521.6807646110717, ep_step: 1000 +2023-05-26 14:21:13 - SimpleLog - INFO: - episode: 1436, ep_reward: 310.13613976845045, ep_step: 1000 +2023-05-26 14:21:15 - SimpleLog - INFO: - episode: 1437, ep_reward: 139.23511179656617, ep_step: 1000 +2023-05-26 14:21:17 - SimpleLog - INFO: - episode: 1438, ep_reward: 523.9340307032405, ep_step: 1000 +2023-05-26 14:21:18 - SimpleLog - INFO: - episode: 1439, ep_reward: 716.3625660390918, ep_step: 1000 +2023-05-26 14:21:20 - SimpleLog - INFO: - episode: 1440, ep_reward: 334.43437342951984, ep_step: 1000 +2023-05-26 14:21:22 - SimpleLog - INFO: - episode: 1441, ep_reward: 639.7752856148112, ep_step: 1000 +2023-05-26 14:21:24 - SimpleLog - INFO: - episode: 1442, ep_reward: 512.4892158565569, ep_step: 1000 +2023-05-26 14:21:26 - SimpleLog - INFO: - episode: 1443, ep_reward: 381.5093405684012, ep_step: 1000 +2023-05-26 14:21:28 - SimpleLog - INFO: - episode: 1444, ep_reward: 487.1675791767275, ep_step: 1000 +2023-05-26 14:21:30 - SimpleLog - INFO: - episode: 1445, ep_reward: 380.1942852902929, ep_step: 1000 +2023-05-26 14:21:32 - SimpleLog - INFO: - episode: 1446, ep_reward: 699.6676973951649, ep_step: 1000 +2023-05-26 14:21:34 - SimpleLog - INFO: - episode: 1447, ep_reward: 782.5097214129901, ep_step: 1000 +2023-05-26 14:21:35 - SimpleLog - INFO: - episode: 1448, ep_reward: 611.7770867010756, ep_step: 1000 +2023-05-26 14:21:37 - SimpleLog - INFO: - episode: 1449, ep_reward: 433.8562770330032, ep_step: 1000 +2023-05-26 14:21:38 - SimpleLog - INFO: - episode: 1450, ep_reward: 675.6457855053338, ep_step: 1000 +2023-05-26 14:21:40 - SimpleLog - INFO: - episode: 1451, ep_reward: 435.5400335919374, ep_step: 1000 +2023-05-26 14:21:42 - SimpleLog - INFO: - episode: 1452, ep_reward: 363.5320105844363, ep_step: 1000 +2023-05-26 14:21:44 - SimpleLog - INFO: - episode: 1453, ep_reward: 426.6578844822609, ep_step: 1000 +2023-05-26 14:21:45 - SimpleLog - INFO: - episode: 1454, ep_reward: 473.0550630617226, ep_step: 1000 +2023-05-26 14:21:47 - SimpleLog - INFO: - episode: 1455, ep_reward: 357.70038651552136, ep_step: 1000 +2023-05-26 14:21:49 - SimpleLog - INFO: - episode: 1456, ep_reward: 629.0762035345671, ep_step: 1000 +2023-05-26 14:21:50 - SimpleLog - INFO: - episode: 1457, ep_reward: 448.7441670104455, ep_step: 1000 +2023-05-26 14:21:52 - SimpleLog - INFO: - episode: 1458, ep_reward: 468.1698948823095, ep_step: 1000 +2023-05-26 14:21:54 - SimpleLog - INFO: - episode: 1459, ep_reward: 653.8315384631245, ep_step: 1000 +2023-05-26 14:21:55 - SimpleLog - INFO: - episode: 1460, ep_reward: 298.4376270538923, ep_step: 1000 +2023-05-26 14:21:57 - SimpleLog - INFO: - episode: 1461, ep_reward: 898.1334566165401, ep_step: 1000 +2023-05-26 14:21:59 - SimpleLog - INFO: - episode: 1462, ep_reward: 382.51040700683234, ep_step: 1000 +2023-05-26 14:22:00 - SimpleLog - INFO: - episode: 1463, ep_reward: 524.188066338006, ep_step: 1000 +2023-05-26 14:22:02 - SimpleLog - INFO: - episode: 1464, ep_reward: 315.3035038998052, ep_step: 1000 +2023-05-26 14:22:04 - SimpleLog - INFO: - episode: 1465, ep_reward: 346.20525502829264, ep_step: 1000 +2023-05-26 14:22:05 - SimpleLog - INFO: - episode: 1466, ep_reward: 588.7075645960335, ep_step: 1000 +2023-05-26 14:22:07 - SimpleLog - INFO: - episode: 1467, ep_reward: 294.1261236139078, ep_step: 1000 +2023-05-26 14:22:09 - SimpleLog - INFO: - episode: 1468, ep_reward: 472.6868987165959, ep_step: 1000 +2023-05-26 14:22:10 - SimpleLog - INFO: - episode: 1469, ep_reward: 623.9901624917136, ep_step: 1000 +2023-05-26 14:22:12 - SimpleLog - INFO: - episode: 1470, ep_reward: 720.3096851027368, ep_step: 1000 +2023-05-26 14:22:14 - SimpleLog - INFO: - episode: 1471, ep_reward: 703.9134352025128, ep_step: 1000 +2023-05-26 14:22:16 - SimpleLog - INFO: - episode: 1472, ep_reward: 426.8892313424026, ep_step: 1000 +2023-05-26 14:22:17 - SimpleLog - INFO: - episode: 1473, ep_reward: 357.3335308800407, ep_step: 1000 +2023-05-26 14:22:19 - SimpleLog - INFO: - episode: 1474, ep_reward: 138.25890925520235, ep_step: 1000 +2023-05-26 14:22:21 - SimpleLog - INFO: - episode: 1475, ep_reward: 377.9009147457546, ep_step: 1000 +2023-05-26 14:22:23 - SimpleLog - INFO: - episode: 1476, ep_reward: 521.3743023865277, ep_step: 1000 +2023-05-26 14:22:24 - SimpleLog - INFO: - episode: 1477, ep_reward: 758.6210099434031, ep_step: 1000 +2023-05-26 14:22:26 - SimpleLog - INFO: - episode: 1478, ep_reward: 533.0568899567156, ep_step: 1000 +2023-05-26 14:22:28 - SimpleLog - INFO: - episode: 1479, ep_reward: 392.8832072187523, ep_step: 1000 +2023-05-26 14:22:30 - SimpleLog - INFO: - episode: 1480, ep_reward: 551.0697776654962, ep_step: 1000 +2023-05-26 14:22:32 - SimpleLog - INFO: - episode: 1481, ep_reward: 479.05609323658706, ep_step: 1000 +2023-05-26 14:22:33 - SimpleLog - INFO: - episode: 1482, ep_reward: 660.4914246088631, ep_step: 1000 +2023-05-26 14:22:36 - SimpleLog - INFO: - episode: 1483, ep_reward: 1175.1617147623595, ep_step: 1000 +2023-05-26 14:22:38 - SimpleLog - INFO: - episode: 1484, ep_reward: 189.8768612387899, ep_step: 1000 +2023-05-26 14:22:39 - SimpleLog - INFO: - episode: 1485, ep_reward: 793.0392570181622, ep_step: 1000 +2023-05-26 14:22:41 - SimpleLog - INFO: - episode: 1486, ep_reward: 472.0531763850763, ep_step: 1000 +2023-05-26 14:22:43 - SimpleLog - INFO: - episode: 1487, ep_reward: 842.2823400151307, ep_step: 1000 +2023-05-26 14:22:45 - SimpleLog - INFO: - episode: 1488, ep_reward: 569.5506301220139, ep_step: 1000 +2023-05-26 14:22:46 - SimpleLog - INFO: - episode: 1489, ep_reward: 978.5526573375773, ep_step: 1000 +2023-05-26 14:22:48 - SimpleLog - INFO: - episode: 1490, ep_reward: 656.4760102684287, ep_step: 1000 +2023-05-26 14:22:50 - SimpleLog - INFO: - episode: 1491, ep_reward: 914.3518763915085, ep_step: 1000 +2023-05-26 14:22:52 - SimpleLog - INFO: - episode: 1492, ep_reward: 291.6825710398675, ep_step: 1000 +2023-05-26 14:22:53 - SimpleLog - INFO: - episode: 1493, ep_reward: 860.7320654674419, ep_step: 1000 +2023-05-26 14:22:55 - SimpleLog - INFO: - episode: 1494, ep_reward: 683.189517369581, ep_step: 1000 +2023-05-26 14:22:57 - SimpleLog - INFO: - episode: 1495, ep_reward: 800.4685799530722, ep_step: 1000 +2023-05-26 14:22:58 - SimpleLog - INFO: - episode: 1496, ep_reward: 702.9744910542977, ep_step: 1000 +2023-05-26 14:23:00 - SimpleLog - INFO: - episode: 1497, ep_reward: 458.07522642560576, ep_step: 1000 +2023-05-26 14:23:02 - SimpleLog - INFO: - episode: 1498, ep_reward: 404.1076565839824, ep_step: 1000 +2023-05-26 14:23:04 - SimpleLog - INFO: - episode: 1499, ep_reward: 378.80940658693754, ep_step: 1000 +2023-05-26 14:23:05 - SimpleLog - INFO: - episode: 1500, ep_reward: 394.4959890517195, ep_step: 1000 +2023-05-26 14:23:07 - SimpleLog - INFO: - episode: 1501, ep_reward: 434.2033388962653, ep_step: 1000 +2023-05-26 14:23:09 - SimpleLog - INFO: - episode: 1502, ep_reward: 613.6134166812884, ep_step: 1000 +2023-05-26 14:23:11 - SimpleLog - INFO: - episode: 1503, ep_reward: 1045.7114175582699, ep_step: 1000 +2023-05-26 14:23:12 - SimpleLog - INFO: - episode: 1504, ep_reward: 748.3534290201254, ep_step: 1000 +2023-05-26 14:23:14 - SimpleLog - INFO: - episode: 1505, ep_reward: 656.7977252776616, ep_step: 1000 +2023-05-26 14:23:15 - SimpleLog - INFO: - episode: 1506, ep_reward: 746.1456981386384, ep_step: 1000 +2023-05-26 14:23:17 - SimpleLog - INFO: - episode: 1507, ep_reward: 446.7060528503488, ep_step: 1000 +2023-05-26 14:23:19 - SimpleLog - INFO: - episode: 1508, ep_reward: 516.949948831986, ep_step: 1000 +2023-05-26 14:23:20 - SimpleLog - INFO: - episode: 1509, ep_reward: 507.6595011960981, ep_step: 1000 +2023-05-26 14:23:22 - SimpleLog - INFO: - episode: 1510, ep_reward: 204.30145112504465, ep_step: 1000 +2023-05-26 14:23:24 - SimpleLog - INFO: - episode: 1511, ep_reward: 505.3281939985684, ep_step: 1000 +2023-05-26 14:23:25 - SimpleLog - INFO: - episode: 1512, ep_reward: 713.1515064607458, ep_step: 1000 +2023-05-26 14:23:27 - SimpleLog - INFO: - episode: 1513, ep_reward: 308.7936670846915, ep_step: 1000 +2023-05-26 14:23:29 - SimpleLog - INFO: - episode: 1514, ep_reward: 695.2015068282712, ep_step: 1000 +2023-05-26 14:23:30 - SimpleLog - INFO: - episode: 1515, ep_reward: 651.7485536252959, ep_step: 1000 +2023-05-26 14:23:32 - SimpleLog - INFO: - episode: 1516, ep_reward: 601.0340400581807, ep_step: 1000 +2023-05-26 14:23:34 - SimpleLog - INFO: - episode: 1517, ep_reward: 354.5714674359154, ep_step: 1000 +2023-05-26 14:23:35 - SimpleLog - INFO: - episode: 1518, ep_reward: 349.6936502188449, ep_step: 1000 +2023-05-26 14:23:37 - SimpleLog - INFO: - episode: 1519, ep_reward: 523.9148303642191, ep_step: 1000 +2023-05-26 14:23:39 - SimpleLog - INFO: - episode: 1520, ep_reward: 442.9756491150341, ep_step: 1000 +2023-05-26 14:23:40 - SimpleLog - INFO: - episode: 1521, ep_reward: 1037.0775394592395, ep_step: 1000 +2023-05-26 14:23:43 - SimpleLog - INFO: - episode: 1522, ep_reward: 424.7513878723647, ep_step: 1000 +2023-05-26 14:23:45 - SimpleLog - INFO: - episode: 1523, ep_reward: 419.77731772991564, ep_step: 1000 +2023-05-26 14:23:46 - SimpleLog - INFO: - episode: 1524, ep_reward: 1142.573618593759, ep_step: 1000 +2023-05-26 14:23:48 - SimpleLog - INFO: - episode: 1525, ep_reward: 371.95388323064117, ep_step: 1000 +2023-05-26 14:23:49 - SimpleLog - INFO: - episode: 1526, ep_reward: 745.7935796001309, ep_step: 1000 +2023-05-26 14:23:51 - SimpleLog - INFO: - episode: 1527, ep_reward: 498.2057143367068, ep_step: 1000 +2023-05-26 14:23:53 - SimpleLog - INFO: - episode: 1528, ep_reward: 546.0252812020195, ep_step: 1000 +2023-05-26 14:23:55 - SimpleLog - INFO: - episode: 1529, ep_reward: 503.0915718841461, ep_step: 1000 +2023-05-26 14:23:56 - SimpleLog - INFO: - episode: 1530, ep_reward: 139.9537196476897, ep_step: 1000 +2023-05-26 14:23:58 - SimpleLog - INFO: - episode: 1531, ep_reward: 505.4736307418131, ep_step: 1000 +2023-05-26 14:24:00 - SimpleLog - INFO: - episode: 1532, ep_reward: 421.7572299297491, ep_step: 1000 +2023-05-26 14:24:01 - SimpleLog - INFO: - episode: 1533, ep_reward: 614.2511670980784, ep_step: 1000 +2023-05-26 14:24:03 - SimpleLog - INFO: - episode: 1534, ep_reward: 469.33415916417346, ep_step: 1000 +2023-05-26 14:24:09 - SimpleLog - INFO: - update_step: 6000, online_eval_reward: 380.705 +2023-05-26 14:24:09 - SimpleLog - INFO: - episode: 1535, ep_reward: 659.7963919964745, ep_step: 1000 +2023-05-26 14:24:11 - SimpleLog - INFO: - episode: 1536, ep_reward: 676.0068246696895, ep_step: 1000 +2023-05-26 14:24:12 - SimpleLog - INFO: - episode: 1537, ep_reward: 253.55118259757222, ep_step: 1000 +2023-05-26 14:24:13 - SimpleLog - INFO: - episode: 1538, ep_reward: 507.2322976425464, ep_step: 1000 +2023-05-26 14:24:14 - SimpleLog - INFO: - episode: 1539, ep_reward: 347.1273755126676, ep_step: 1000 +2023-05-26 14:24:16 - SimpleLog - INFO: - episode: 1540, ep_reward: 424.19940547754993, ep_step: 1000 +2023-05-26 14:24:17 - SimpleLog - INFO: - episode: 1541, ep_reward: 187.51723976000886, ep_step: 1000 +2023-05-26 14:24:19 - SimpleLog - INFO: - episode: 1542, ep_reward: 48.54681185821514, ep_step: 1000 +2023-05-26 14:24:20 - SimpleLog - INFO: - episode: 1543, ep_reward: 549.3039918507624, ep_step: 1000 +2023-05-26 14:24:21 - SimpleLog - INFO: - episode: 1544, ep_reward: 298.17976423709365, ep_step: 1000 +2023-05-26 14:24:23 - SimpleLog - INFO: - episode: 1545, ep_reward: 116.77634549044186, ep_step: 1000 +2023-05-26 14:24:25 - SimpleLog - INFO: - episode: 1546, ep_reward: 314.2900794571644, ep_step: 1000 +2023-05-26 14:24:27 - SimpleLog - INFO: - episode: 1547, ep_reward: 454.9087477482498, ep_step: 1000 +2023-05-26 14:24:28 - SimpleLog - INFO: - episode: 1548, ep_reward: 88.13749780477535, ep_step: 1000 +2023-05-26 14:24:30 - SimpleLog - INFO: - episode: 1549, ep_reward: 269.2161102063471, ep_step: 1000 +2023-05-26 14:24:32 - SimpleLog - INFO: - episode: 1550, ep_reward: 433.1097770689753, ep_step: 1000 +2023-05-26 14:24:34 - SimpleLog - INFO: - episode: 1551, ep_reward: 331.4561437861965, ep_step: 1000 +2023-05-26 14:24:35 - SimpleLog - INFO: - episode: 1552, ep_reward: 290.2082296448547, ep_step: 1000 +2023-05-26 14:24:37 - SimpleLog - INFO: - episode: 1553, ep_reward: 310.1519427142127, ep_step: 1000 +2023-05-26 14:24:39 - SimpleLog - INFO: - episode: 1554, ep_reward: 324.27465965425915, ep_step: 1000 +2023-05-26 14:24:41 - SimpleLog - INFO: - episode: 1555, ep_reward: 451.7989630970613, ep_step: 1000 +2023-05-26 14:24:42 - SimpleLog - INFO: - episode: 1556, ep_reward: 224.67611474426474, ep_step: 1000 +2023-05-26 14:24:44 - SimpleLog - INFO: - episode: 1557, ep_reward: 437.73115162495145, ep_step: 1000 +2023-05-26 14:24:46 - SimpleLog - INFO: - episode: 1558, ep_reward: 488.58199925610757, ep_step: 1000 +2023-05-26 14:24:48 - SimpleLog - INFO: - episode: 1559, ep_reward: 225.2739601520186, ep_step: 1000 +2023-05-26 14:24:50 - SimpleLog - INFO: - episode: 1560, ep_reward: 372.1759356197966, ep_step: 1000 +2023-05-26 14:24:52 - SimpleLog - INFO: - episode: 1561, ep_reward: 326.53616500189264, ep_step: 1000 +2023-05-26 14:24:54 - SimpleLog - INFO: - episode: 1562, ep_reward: 355.7580480942167, ep_step: 1000 +2023-05-26 14:24:55 - SimpleLog - INFO: - episode: 1563, ep_reward: 634.2268112714054, ep_step: 1000 +2023-05-26 14:24:57 - SimpleLog - INFO: - episode: 1564, ep_reward: 210.24196355510034, ep_step: 1000 +2023-05-26 14:24:59 - SimpleLog - INFO: - episode: 1565, ep_reward: 270.4253913048835, ep_step: 1000 +2023-05-26 14:25:01 - SimpleLog - INFO: - episode: 1566, ep_reward: 193.80175218051687, ep_step: 1000 +2023-05-26 14:25:03 - SimpleLog - INFO: - episode: 1567, ep_reward: 336.1390866164576, ep_step: 1000 +2023-05-26 14:25:04 - SimpleLog - INFO: - episode: 1568, ep_reward: 574.1570321933473, ep_step: 1000 +2023-05-26 14:25:06 - SimpleLog - INFO: - episode: 1569, ep_reward: 439.3523895166446, ep_step: 1000 +2023-05-26 14:25:08 - SimpleLog - INFO: - episode: 1570, ep_reward: -174.2765221183658, ep_step: 1000 +2023-05-26 14:25:09 - SimpleLog - INFO: - episode: 1571, ep_reward: 379.6124218655388, ep_step: 1000 +2023-05-26 14:25:11 - SimpleLog - INFO: - episode: 1572, ep_reward: 288.46748006457267, ep_step: 1000 +2023-05-26 14:25:13 - SimpleLog - INFO: - episode: 1573, ep_reward: 636.8141427869051, ep_step: 1000 +2023-05-26 14:25:14 - SimpleLog - INFO: - episode: 1574, ep_reward: 677.5897363850927, ep_step: 1000 +2023-05-26 14:25:16 - SimpleLog - INFO: - episode: 1575, ep_reward: 547.4608051998218, ep_step: 1000 +2023-05-26 14:25:18 - SimpleLog - INFO: - episode: 1576, ep_reward: 358.1239757927589, ep_step: 1000 +2023-05-26 14:25:20 - SimpleLog - INFO: - episode: 1577, ep_reward: 502.22676196550134, ep_step: 1000 +2023-05-26 14:25:21 - SimpleLog - INFO: - episode: 1578, ep_reward: 250.90210549130842, ep_step: 1000 +2023-05-26 14:25:23 - SimpleLog - INFO: - episode: 1579, ep_reward: 368.5925151703353, ep_step: 1000 +2023-05-26 14:25:25 - SimpleLog - INFO: - episode: 1580, ep_reward: 445.24933898803846, ep_step: 1000 +2023-05-26 14:25:27 - SimpleLog - INFO: - episode: 1581, ep_reward: 374.28860689333936, ep_step: 1000 +2023-05-26 14:25:29 - SimpleLog - INFO: - episode: 1582, ep_reward: 316.416748011816, ep_step: 1000 +2023-05-26 14:25:31 - SimpleLog - INFO: - episode: 1583, ep_reward: 274.48526400027475, ep_step: 1000 +2023-05-26 14:25:32 - SimpleLog - INFO: - episode: 1584, ep_reward: 445.49139661747773, ep_step: 1000 +2023-05-26 14:25:34 - SimpleLog - INFO: - episode: 1585, ep_reward: 396.5912986686092, ep_step: 1000 +2023-05-26 14:25:36 - SimpleLog - INFO: - episode: 1586, ep_reward: 626.289284738639, ep_step: 1000 +2023-05-26 14:25:38 - SimpleLog - INFO: - episode: 1587, ep_reward: 86.53872888357334, ep_step: 1000 +2023-05-26 14:25:39 - SimpleLog - INFO: - episode: 1588, ep_reward: 280.2245593116199, ep_step: 1000 +2023-05-26 14:25:41 - SimpleLog - INFO: - episode: 1589, ep_reward: 334.0020389297851, ep_step: 1000 +2023-05-26 14:25:43 - SimpleLog - INFO: - episode: 1590, ep_reward: 506.3473887201669, ep_step: 1000 +2023-05-26 14:25:44 - SimpleLog - INFO: - episode: 1591, ep_reward: 153.18969531801753, ep_step: 1000 +2023-05-26 14:25:46 - SimpleLog - INFO: - episode: 1592, ep_reward: 131.03450913360086, ep_step: 1000 +2023-05-26 14:25:48 - SimpleLog - INFO: - episode: 1593, ep_reward: 336.1185632559088, ep_step: 1000 +2023-05-26 14:25:49 - SimpleLog - INFO: - episode: 1594, ep_reward: 351.2407550857679, ep_step: 1000 +2023-05-26 14:25:51 - SimpleLog - INFO: - episode: 1595, ep_reward: 375.97542743400925, ep_step: 1000 +2023-05-26 14:25:53 - SimpleLog - INFO: - episode: 1596, ep_reward: 143.89574696109028, ep_step: 1000 +2023-05-26 14:25:55 - SimpleLog - INFO: - episode: 1597, ep_reward: 251.2073345755846, ep_step: 1000 +2023-05-26 14:25:57 - SimpleLog - INFO: - episode: 1598, ep_reward: 431.1271905691266, ep_step: 1000 +2023-05-26 14:25:59 - SimpleLog - INFO: - episode: 1599, ep_reward: 220.17005491605312, ep_step: 1000 +2023-05-26 14:26:00 - SimpleLog - INFO: - episode: 1600, ep_reward: 352.9293384053734, ep_step: 1000 +2023-05-26 14:26:02 - SimpleLog - INFO: - episode: 1601, ep_reward: 490.29834447434143, ep_step: 1000 +2023-05-26 14:26:04 - SimpleLog - INFO: - episode: 1602, ep_reward: 298.5663765203426, ep_step: 1000 +2023-05-26 14:26:05 - SimpleLog - INFO: - episode: 1603, ep_reward: 191.47944945125707, ep_step: 1000 +2023-05-26 14:26:07 - SimpleLog - INFO: - episode: 1604, ep_reward: 573.3703016790149, ep_step: 1000 +2023-05-26 14:26:09 - SimpleLog - INFO: - episode: 1605, ep_reward: 489.3686885839171, ep_step: 1000 +2023-05-26 14:26:11 - SimpleLog - INFO: - episode: 1606, ep_reward: 650.906798036625, ep_step: 1000 +2023-05-26 14:26:12 - SimpleLog - INFO: - episode: 1607, ep_reward: 305.9915917832516, ep_step: 1000 +2023-05-26 14:26:14 - SimpleLog - INFO: - episode: 1608, ep_reward: 126.8466254092639, ep_step: 1000 +2023-05-26 14:26:16 - SimpleLog - INFO: - episode: 1609, ep_reward: 303.14734678090116, ep_step: 1000 +2023-05-26 14:26:17 - SimpleLog - INFO: - episode: 1610, ep_reward: 668.8659483447856, ep_step: 1000 +2023-05-26 14:26:19 - SimpleLog - INFO: - episode: 1611, ep_reward: -115.79566581575499, ep_step: 1000 +2023-05-26 14:26:21 - SimpleLog - INFO: - episode: 1612, ep_reward: 681.2266440754148, ep_step: 1000 +2023-05-26 14:26:23 - SimpleLog - INFO: - episode: 1613, ep_reward: 293.0054235313454, ep_step: 1000 +2023-05-26 14:26:25 - SimpleLog - INFO: - episode: 1614, ep_reward: 418.1544468441948, ep_step: 1000 +2023-05-26 14:26:26 - SimpleLog - INFO: - episode: 1615, ep_reward: 268.45535740877983, ep_step: 1000 +2023-05-26 14:26:28 - SimpleLog - INFO: - episode: 1616, ep_reward: 88.3976536104436, ep_step: 1000 +2023-05-26 14:26:30 - SimpleLog - INFO: - episode: 1617, ep_reward: 742.4634039577846, ep_step: 1000 +2023-05-26 14:26:31 - SimpleLog - INFO: - episode: 1618, ep_reward: 708.6586766676205, ep_step: 1000 +2023-05-26 14:26:33 - SimpleLog - INFO: - episode: 1619, ep_reward: 319.9610930924099, ep_step: 1000 +2023-05-26 14:26:35 - SimpleLog - INFO: - episode: 1620, ep_reward: 393.8341322967279, ep_step: 1000 +2023-05-26 14:26:37 - SimpleLog - INFO: - episode: 1621, ep_reward: 567.6000181919433, ep_step: 1000 +2023-05-26 14:26:38 - SimpleLog - INFO: - episode: 1622, ep_reward: 445.3091691690136, ep_step: 1000 +2023-05-26 14:26:40 - SimpleLog - INFO: - episode: 1623, ep_reward: 202.7852354121587, ep_step: 1000 +2023-05-26 14:26:42 - SimpleLog - INFO: - episode: 1624, ep_reward: 106.3881561901384, ep_step: 1000 +2023-05-26 14:26:44 - SimpleLog - INFO: - episode: 1625, ep_reward: 306.28020037828264, ep_step: 1000 +2023-05-26 14:26:45 - SimpleLog - INFO: - episode: 1626, ep_reward: 620.2656221810911, ep_step: 1000 +2023-05-26 14:26:47 - SimpleLog - INFO: - episode: 1627, ep_reward: 405.2172402290932, ep_step: 1000 +2023-05-26 14:26:49 - SimpleLog - INFO: - episode: 1628, ep_reward: 34.15795794014862, ep_step: 1000 +2023-05-26 14:26:51 - SimpleLog - INFO: - episode: 1629, ep_reward: 419.75231120289806, ep_step: 1000 +2023-05-26 14:26:52 - SimpleLog - INFO: - episode: 1630, ep_reward: 463.63723824104756, ep_step: 1000 +2023-05-26 14:26:54 - SimpleLog - INFO: - episode: 1631, ep_reward: -129.99008306832846, ep_step: 1000 +2023-05-26 14:26:56 - SimpleLog - INFO: - episode: 1632, ep_reward: 331.48099952016304, ep_step: 1000 +2023-05-26 14:26:57 - SimpleLog - INFO: - episode: 1633, ep_reward: 367.3787417195847, ep_step: 1000 +2023-05-26 14:27:00 - SimpleLog - INFO: - episode: 1634, ep_reward: 363.3533278857063, ep_step: 1000 +2023-05-26 14:27:02 - SimpleLog - INFO: - episode: 1635, ep_reward: 365.17026051919265, ep_step: 1000 +2023-05-26 14:27:04 - SimpleLog - INFO: - episode: 1636, ep_reward: 471.5973070522795, ep_step: 1000 +2023-05-26 14:27:05 - SimpleLog - INFO: - episode: 1637, ep_reward: 296.0694943882472, ep_step: 1000 +2023-05-26 14:27:07 - SimpleLog - INFO: - episode: 1638, ep_reward: 166.11683273444737, ep_step: 1000 +2023-05-26 14:27:09 - SimpleLog - INFO: - episode: 1639, ep_reward: -94.47413311187496, ep_step: 1000 +2023-05-26 14:27:11 - SimpleLog - INFO: - episode: 1640, ep_reward: 223.4020686356167, ep_step: 1000 +2023-05-26 14:27:12 - SimpleLog - INFO: - episode: 1641, ep_reward: 545.7586956441904, ep_step: 1000 +2023-05-26 14:27:14 - SimpleLog - INFO: - episode: 1642, ep_reward: 288.816596201964, ep_step: 1000 +2023-05-26 14:27:16 - SimpleLog - INFO: - episode: 1643, ep_reward: 329.26455879191735, ep_step: 1000 +2023-05-26 14:27:17 - SimpleLog - INFO: - episode: 1644, ep_reward: 241.30307770152933, ep_step: 1000 +2023-05-26 14:27:19 - SimpleLog - INFO: - episode: 1645, ep_reward: 503.93513415088626, ep_step: 1000 +2023-05-26 14:27:21 - SimpleLog - INFO: - episode: 1646, ep_reward: 90.14693917617808, ep_step: 1000 +2023-05-26 14:27:23 - SimpleLog - INFO: - episode: 1647, ep_reward: 276.33163969899095, ep_step: 1000 +2023-05-26 14:27:25 - SimpleLog - INFO: - episode: 1648, ep_reward: 194.22378975637938, ep_step: 1000 +2023-05-26 14:27:26 - SimpleLog - INFO: - episode: 1649, ep_reward: 327.53729071132113, ep_step: 1000 +2023-05-26 14:27:28 - SimpleLog - INFO: - episode: 1650, ep_reward: 250.8961160030949, ep_step: 1000 +2023-05-26 14:27:30 - SimpleLog - INFO: - episode: 1651, ep_reward: -106.59469119380336, ep_step: 1000 +2023-05-26 14:27:31 - SimpleLog - INFO: - episode: 1652, ep_reward: 296.10226804946757, ep_step: 1000 +2023-05-26 14:27:33 - SimpleLog - INFO: - episode: 1653, ep_reward: 136.2120359911043, ep_step: 1000 +2023-05-26 14:27:35 - SimpleLog - INFO: - episode: 1654, ep_reward: 190.63641577291656, ep_step: 1000 +2023-05-26 14:27:37 - SimpleLog - INFO: - episode: 1655, ep_reward: 210.20461764232212, ep_step: 1000 +2023-05-26 14:27:38 - SimpleLog - INFO: - episode: 1656, ep_reward: 595.7572104734361, ep_step: 1000 +2023-05-26 14:27:40 - SimpleLog - INFO: - episode: 1657, ep_reward: 269.0302125875577, ep_step: 1000 +2023-05-26 14:27:42 - SimpleLog - INFO: - episode: 1658, ep_reward: 358.589310299457, ep_step: 1000 +2023-05-26 14:27:44 - SimpleLog - INFO: - episode: 1659, ep_reward: 482.2673068193407, ep_step: 1000 +2023-05-26 14:27:45 - SimpleLog - INFO: - episode: 1660, ep_reward: 530.0688934792413, ep_step: 1000 +2023-05-26 14:27:47 - SimpleLog - INFO: - episode: 1661, ep_reward: 232.37951735379076, ep_step: 1000 +2023-05-26 14:27:49 - SimpleLog - INFO: - episode: 1662, ep_reward: 263.5048604037952, ep_step: 1000 +2023-05-26 14:27:56 - SimpleLog - INFO: - update_step: 6500, online_eval_reward: 418.540 +2023-05-26 14:27:56 - SimpleLog - INFO: - episode: 1663, ep_reward: 478.024714977645, ep_step: 1000 +2023-05-26 14:27:57 - SimpleLog - INFO: - episode: 1664, ep_reward: 819.4215880514785, ep_step: 1000 +2023-05-26 14:27:58 - SimpleLog - INFO: - episode: 1665, ep_reward: 229.68788227456653, ep_step: 1000 +2023-05-26 14:28:00 - SimpleLog - INFO: - episode: 1666, ep_reward: 233.92447318586335, ep_step: 1000 +2023-05-26 14:28:01 - SimpleLog - INFO: - episode: 1667, ep_reward: 137.0744261820348, ep_step: 1000 +2023-05-26 14:28:02 - SimpleLog - INFO: - episode: 1668, ep_reward: 271.81386671446654, ep_step: 1000 +2023-05-26 14:28:04 - SimpleLog - INFO: - episode: 1669, ep_reward: 385.48479821810866, ep_step: 1000 +2023-05-26 14:28:05 - SimpleLog - INFO: - episode: 1670, ep_reward: 660.2220883204448, ep_step: 1000 +2023-05-26 14:28:08 - SimpleLog - INFO: - episode: 1671, ep_reward: 676.121132300966, ep_step: 1000 +2023-05-26 14:28:10 - SimpleLog - INFO: - episode: 1672, ep_reward: 261.067692900878, ep_step: 1000 +2023-05-26 14:28:12 - SimpleLog - INFO: - episode: 1673, ep_reward: 382.5150074571063, ep_step: 1000 +2023-05-26 14:28:13 - SimpleLog - INFO: - episode: 1674, ep_reward: 647.2901715069582, ep_step: 1000 +2023-05-26 14:28:15 - SimpleLog - INFO: - episode: 1675, ep_reward: 418.13385256719863, ep_step: 1000 +2023-05-26 14:28:17 - SimpleLog - INFO: - episode: 1676, ep_reward: 218.80375832824748, ep_step: 1000 +2023-05-26 14:28:18 - SimpleLog - INFO: - episode: 1677, ep_reward: 652.5472494782861, ep_step: 1000 +2023-05-26 14:28:20 - SimpleLog - INFO: - episode: 1678, ep_reward: 423.7931940890479, ep_step: 1000 +2023-05-26 14:28:22 - SimpleLog - INFO: - episode: 1679, ep_reward: 437.8967640362189, ep_step: 1000 +2023-05-26 14:28:24 - SimpleLog - INFO: - episode: 1680, ep_reward: 440.20208624623797, ep_step: 1000 +2023-05-26 14:28:25 - SimpleLog - INFO: - episode: 1681, ep_reward: 432.58588576973307, ep_step: 1000 +2023-05-26 14:28:27 - SimpleLog - INFO: - episode: 1682, ep_reward: 108.55472516761532, ep_step: 1000 +2023-05-26 14:28:29 - SimpleLog - INFO: - episode: 1683, ep_reward: 427.7648602866392, ep_step: 1000 +2023-05-26 14:28:31 - SimpleLog - INFO: - episode: 1684, ep_reward: 421.0660405581282, ep_step: 1000 +2023-05-26 14:28:32 - SimpleLog - INFO: - episode: 1685, ep_reward: 356.3668380762236, ep_step: 1000 +2023-05-26 14:28:34 - SimpleLog - INFO: - episode: 1686, ep_reward: 308.3173986526929, ep_step: 1000 +2023-05-26 14:28:36 - SimpleLog - INFO: - episode: 1687, ep_reward: 300.7805539507573, ep_step: 1000 +2023-05-26 14:28:38 - SimpleLog - INFO: - episode: 1688, ep_reward: 480.8190213521909, ep_step: 1000 +2023-05-26 14:28:39 - SimpleLog - INFO: - episode: 1689, ep_reward: 423.50628985856906, ep_step: 1000 +2023-05-26 14:28:41 - SimpleLog - INFO: - episode: 1690, ep_reward: 498.30731710738775, ep_step: 1000 +2023-05-26 14:28:43 - SimpleLog - INFO: - episode: 1691, ep_reward: 472.2935654108509, ep_step: 1000 +2023-05-26 14:28:45 - SimpleLog - INFO: - episode: 1692, ep_reward: 393.3376057793132, ep_step: 1000 +2023-05-26 14:28:46 - SimpleLog - INFO: - episode: 1693, ep_reward: 444.1283569693961, ep_step: 1000 +2023-05-26 14:28:48 - SimpleLog - INFO: - episode: 1694, ep_reward: 533.1504910111893, ep_step: 1000 +2023-05-26 14:28:50 - SimpleLog - INFO: - episode: 1695, ep_reward: 317.8997627122442, ep_step: 1000 +2023-05-26 14:28:51 - SimpleLog - INFO: - episode: 1696, ep_reward: 253.332307280282, ep_step: 1000 +2023-05-26 14:28:53 - SimpleLog - INFO: - episode: 1697, ep_reward: 426.099537544452, ep_step: 1000 +2023-05-26 14:28:55 - SimpleLog - INFO: - episode: 1698, ep_reward: 469.64710895014593, ep_step: 1000 +2023-05-26 14:28:56 - SimpleLog - INFO: - episode: 1699, ep_reward: 278.41411311184237, ep_step: 1000 +2023-05-26 14:28:58 - SimpleLog - INFO: - episode: 1700, ep_reward: 362.03387980969194, ep_step: 1000 +2023-05-26 14:29:00 - SimpleLog - INFO: - episode: 1701, ep_reward: 509.1066718962671, ep_step: 1000 +2023-05-26 14:29:01 - SimpleLog - INFO: - episode: 1702, ep_reward: 727.8169497071674, ep_step: 1000 +2023-05-26 14:29:03 - SimpleLog - INFO: - episode: 1703, ep_reward: 497.90281123188413, ep_step: 1000 +2023-05-26 14:29:05 - SimpleLog - INFO: - episode: 1704, ep_reward: 568.2220373231363, ep_step: 1000 +2023-05-26 14:29:07 - SimpleLog - INFO: - episode: 1705, ep_reward: 551.5042686479069, ep_step: 1000 +2023-05-26 14:29:08 - SimpleLog - INFO: - episode: 1706, ep_reward: 403.12833698355075, ep_step: 1000 +2023-05-26 14:29:10 - SimpleLog - INFO: - episode: 1707, ep_reward: 594.857116603043, ep_step: 1000 +2023-05-26 14:29:12 - SimpleLog - INFO: - episode: 1708, ep_reward: 411.4461806712427, ep_step: 1000 +2023-05-26 14:29:14 - SimpleLog - INFO: - episode: 1709, ep_reward: 484.84930941749735, ep_step: 1000 +2023-05-26 14:29:16 - SimpleLog - INFO: - episode: 1710, ep_reward: 239.18276674838012, ep_step: 1000 +2023-05-26 14:29:18 - SimpleLog - INFO: - episode: 1711, ep_reward: 452.86648358665263, ep_step: 1000 +2023-05-26 14:29:19 - SimpleLog - INFO: - episode: 1712, ep_reward: 411.7094437989933, ep_step: 1000 +2023-05-26 14:29:21 - SimpleLog - INFO: - episode: 1713, ep_reward: 569.3400451126328, ep_step: 1000 +2023-05-26 14:29:23 - SimpleLog - INFO: - episode: 1714, ep_reward: 311.9131307308064, ep_step: 1000 +2023-05-26 14:29:24 - SimpleLog - INFO: - episode: 1715, ep_reward: 585.9392300636202, ep_step: 1000 +2023-05-26 14:29:26 - SimpleLog - INFO: - episode: 1716, ep_reward: 453.5750544544181, ep_step: 1000 +2023-05-26 14:29:28 - SimpleLog - INFO: - episode: 1717, ep_reward: 320.4727223111839, ep_step: 1000 +2023-05-26 14:29:30 - SimpleLog - INFO: - episode: 1718, ep_reward: 220.2256333778901, ep_step: 1000 +2023-05-26 14:29:31 - SimpleLog - INFO: - episode: 1719, ep_reward: 366.4902170274986, ep_step: 1000 +2023-05-26 14:29:33 - SimpleLog - INFO: - episode: 1720, ep_reward: 173.02227741708003, ep_step: 1000 +2023-05-26 14:29:35 - SimpleLog - INFO: - episode: 1721, ep_reward: 276.0819569835713, ep_step: 1000 +2023-05-26 14:29:36 - SimpleLog - INFO: - episode: 1722, ep_reward: 192.5753472371302, ep_step: 1000 +2023-05-26 14:29:38 - SimpleLog - INFO: - episode: 1723, ep_reward: 301.520397135754, ep_step: 1000 +2023-05-26 14:29:40 - SimpleLog - INFO: - episode: 1724, ep_reward: 522.3927791039341, ep_step: 1000 +2023-05-26 14:29:42 - SimpleLog - INFO: - episode: 1725, ep_reward: 730.8232419991078, ep_step: 1000 +2023-05-26 14:29:43 - SimpleLog - INFO: - episode: 1726, ep_reward: 224.11732818459282, ep_step: 1000 +2023-05-26 14:29:45 - SimpleLog - INFO: - episode: 1727, ep_reward: 493.70166541049787, ep_step: 1000 +2023-05-26 14:29:47 - SimpleLog - INFO: - episode: 1728, ep_reward: 568.6107879934643, ep_step: 1000 +2023-05-26 14:29:49 - SimpleLog - INFO: - episode: 1729, ep_reward: 382.8397934281558, ep_step: 1000 +2023-05-26 14:29:50 - SimpleLog - INFO: - episode: 1730, ep_reward: 237.13759658444323, ep_step: 1000 +2023-05-26 14:29:52 - SimpleLog - INFO: - episode: 1731, ep_reward: 213.60810893073796, ep_step: 1000 +2023-05-26 14:29:54 - SimpleLog - INFO: - episode: 1732, ep_reward: 245.77908744094637, ep_step: 1000 +2023-05-26 14:29:56 - SimpleLog - INFO: - episode: 1733, ep_reward: 272.7473938947983, ep_step: 1000 +2023-05-26 14:29:57 - SimpleLog - INFO: - episode: 1734, ep_reward: 215.3048755938701, ep_step: 1000 +2023-05-26 14:29:59 - SimpleLog - INFO: - episode: 1735, ep_reward: 307.4021943512199, ep_step: 1000 +2023-05-26 14:30:01 - SimpleLog - INFO: - episode: 1736, ep_reward: 398.62847495562215, ep_step: 1000 +2023-05-26 14:30:02 - SimpleLog - INFO: - episode: 1737, ep_reward: 149.56751732887253, ep_step: 1000 +2023-05-26 14:30:04 - SimpleLog - INFO: - episode: 1738, ep_reward: 328.2180272321614, ep_step: 1000 +2023-05-26 14:30:06 - SimpleLog - INFO: - episode: 1739, ep_reward: 546.6022984099504, ep_step: 1000 +2023-05-26 14:30:07 - SimpleLog - INFO: - episode: 1740, ep_reward: 681.8185997352834, ep_step: 1000 +2023-05-26 14:30:09 - SimpleLog - INFO: - episode: 1741, ep_reward: 71.5001338821989, ep_step: 1000 +2023-05-26 14:30:11 - SimpleLog - INFO: - episode: 1742, ep_reward: 663.2973265780707, ep_step: 1000 +2023-05-26 14:30:13 - SimpleLog - INFO: - episode: 1743, ep_reward: 385.37885676381586, ep_step: 1000 +2023-05-26 14:30:14 - SimpleLog - INFO: - episode: 1744, ep_reward: 83.2929347066333, ep_step: 1000 +2023-05-26 14:30:16 - SimpleLog - INFO: - episode: 1745, ep_reward: 366.43725893513164, ep_step: 1000 +2023-05-26 14:30:18 - SimpleLog - INFO: - episode: 1746, ep_reward: -77.53503782140089, ep_step: 1000 +2023-05-26 14:30:19 - SimpleLog - INFO: - episode: 1747, ep_reward: 220.8486055048864, ep_step: 1000 +2023-05-26 14:30:22 - SimpleLog - INFO: - episode: 1748, ep_reward: 164.3236376419515, ep_step: 1000 +2023-05-26 14:30:23 - SimpleLog - INFO: - episode: 1749, ep_reward: 204.97497432679017, ep_step: 1000 +2023-05-26 14:30:25 - SimpleLog - INFO: - episode: 1750, ep_reward: 582.8353484737306, ep_step: 1000 +2023-05-26 14:30:27 - SimpleLog - INFO: - episode: 1751, ep_reward: 552.2274031201289, ep_step: 1000 +2023-05-26 14:30:29 - SimpleLog - INFO: - episode: 1752, ep_reward: 401.3328596548242, ep_step: 1000 +2023-05-26 14:30:31 - SimpleLog - INFO: - episode: 1753, ep_reward: 265.94971913321916, ep_step: 1000 +2023-05-26 14:30:32 - SimpleLog - INFO: - episode: 1754, ep_reward: 368.8535873257472, ep_step: 1000 +2023-05-26 14:30:34 - SimpleLog - INFO: - episode: 1755, ep_reward: 257.6320346766231, ep_step: 1000 +2023-05-26 14:30:36 - SimpleLog - INFO: - episode: 1756, ep_reward: 233.44046397482066, ep_step: 1000 +2023-05-26 14:30:38 - SimpleLog - INFO: - episode: 1757, ep_reward: 287.8821056832856, ep_step: 1000 +2023-05-26 14:30:39 - SimpleLog - INFO: - episode: 1758, ep_reward: 474.48336649918474, ep_step: 1000 +2023-05-26 14:30:41 - SimpleLog - INFO: - episode: 1759, ep_reward: 691.465102046938, ep_step: 1000 +2023-05-26 14:30:43 - SimpleLog - INFO: - episode: 1760, ep_reward: 467.75380516457585, ep_step: 1000 +2023-05-26 14:30:44 - SimpleLog - INFO: - episode: 1761, ep_reward: 367.5132952464164, ep_step: 1000 +2023-05-26 14:30:46 - SimpleLog - INFO: - episode: 1762, ep_reward: 728.404921476289, ep_step: 1000 +2023-05-26 14:30:48 - SimpleLog - INFO: - episode: 1763, ep_reward: 428.9356017821629, ep_step: 1000 +2023-05-26 14:30:49 - SimpleLog - INFO: - episode: 1764, ep_reward: 215.47814322181023, ep_step: 1000 +2023-05-26 14:30:51 - SimpleLog - INFO: - episode: 1765, ep_reward: 259.02488230794097, ep_step: 1000 +2023-05-26 14:30:53 - SimpleLog - INFO: - episode: 1766, ep_reward: 479.1792413001838, ep_step: 1000 +2023-05-26 14:30:54 - SimpleLog - INFO: - episode: 1767, ep_reward: 467.4527886832487, ep_step: 1000 +2023-05-26 14:30:56 - SimpleLog - INFO: - episode: 1768, ep_reward: 476.3447217834053, ep_step: 1000 +2023-05-26 14:30:58 - SimpleLog - INFO: - episode: 1769, ep_reward: 442.1524788959993, ep_step: 1000 +2023-05-26 14:30:59 - SimpleLog - INFO: - episode: 1770, ep_reward: 497.74411807249663, ep_step: 1000 +2023-05-26 14:31:01 - SimpleLog - INFO: - episode: 1771, ep_reward: 349.21662926145547, ep_step: 1000 +2023-05-26 14:31:03 - SimpleLog - INFO: - episode: 1772, ep_reward: 505.9608568005308, ep_step: 1000 +2023-05-26 14:31:05 - SimpleLog - INFO: - episode: 1773, ep_reward: 203.14183627209306, ep_step: 1000 +2023-05-26 14:31:07 - SimpleLog - INFO: - episode: 1774, ep_reward: 399.17096586893314, ep_step: 1000 +2023-05-26 14:31:08 - SimpleLog - INFO: - episode: 1775, ep_reward: 595.5173838400767, ep_step: 1000 +2023-05-26 14:31:10 - SimpleLog - INFO: - episode: 1776, ep_reward: 583.8921912294572, ep_step: 1000 +2023-05-26 14:31:12 - SimpleLog - INFO: - episode: 1777, ep_reward: 664.8904368172067, ep_step: 1000 +2023-05-26 14:31:13 - SimpleLog - INFO: - episode: 1778, ep_reward: 193.9692425756692, ep_step: 1000 +2023-05-26 14:31:15 - SimpleLog - INFO: - episode: 1779, ep_reward: 188.18643265140366, ep_step: 1000 +2023-05-26 14:31:17 - SimpleLog - INFO: - episode: 1780, ep_reward: 546.1587778996324, ep_step: 1000 +2023-05-26 14:31:19 - SimpleLog - INFO: - episode: 1781, ep_reward: 235.79319842825763, ep_step: 1000 +2023-05-26 14:31:20 - SimpleLog - INFO: - episode: 1782, ep_reward: 495.82620104888406, ep_step: 1000 +2023-05-26 14:31:22 - SimpleLog - INFO: - episode: 1783, ep_reward: 466.4779534620081, ep_step: 1000 +2023-05-26 14:31:24 - SimpleLog - INFO: - episode: 1784, ep_reward: 215.2503691417038, ep_step: 1000 +2023-05-26 14:31:26 - SimpleLog - INFO: - episode: 1785, ep_reward: 547.5599981655974, ep_step: 1000 +2023-05-26 14:31:28 - SimpleLog - INFO: - episode: 1786, ep_reward: 330.5093045147479, ep_step: 1000 +2023-05-26 14:31:30 - SimpleLog - INFO: - episode: 1787, ep_reward: 684.3682184866843, ep_step: 1000 +2023-05-26 14:31:32 - SimpleLog - INFO: - episode: 1788, ep_reward: 332.51959400589726, ep_step: 1000 +2023-05-26 14:31:34 - SimpleLog - INFO: - episode: 1789, ep_reward: 468.547111362649, ep_step: 1000 +2023-05-26 14:31:36 - SimpleLog - INFO: - episode: 1790, ep_reward: 409.1139348092768, ep_step: 1000 +2023-05-26 14:31:42 - SimpleLog - INFO: - update_step: 7000, online_eval_reward: 194.737 +2023-05-26 14:31:42 - SimpleLog - INFO: - episode: 1791, ep_reward: 526.8383419114364, ep_step: 1000 +2023-05-26 14:31:43 - SimpleLog - INFO: - episode: 1792, ep_reward: 325.5269812969717, ep_step: 1000 +2023-05-26 14:31:45 - SimpleLog - INFO: - episode: 1793, ep_reward: 352.35489603470336, ep_step: 1000 +2023-05-26 14:31:46 - SimpleLog - INFO: - episode: 1794, ep_reward: 539.7595569191719, ep_step: 1000 +2023-05-26 14:31:48 - SimpleLog - INFO: - episode: 1795, ep_reward: 462.9149421852215, ep_step: 1000 +2023-05-26 14:31:49 - SimpleLog - INFO: - episode: 1796, ep_reward: 563.1630397513804, ep_step: 1000 +2023-05-26 14:31:51 - SimpleLog - INFO: - episode: 1797, ep_reward: 666.1053595329748, ep_step: 1000 +2023-05-26 14:31:53 - SimpleLog - INFO: - episode: 1798, ep_reward: 501.6417268829139, ep_step: 1000 +2023-05-26 14:31:55 - SimpleLog - INFO: - episode: 1799, ep_reward: 647.4666950269382, ep_step: 1000 +2023-05-26 14:31:56 - SimpleLog - INFO: - episode: 1800, ep_reward: 373.0252964738777, ep_step: 1000 +2023-05-26 14:31:58 - SimpleLog - INFO: - episode: 1801, ep_reward: 358.01069556081745, ep_step: 1000 +2023-05-26 14:32:00 - SimpleLog - INFO: - episode: 1802, ep_reward: 556.0590203693796, ep_step: 1000 +2023-05-26 14:32:01 - SimpleLog - INFO: - episode: 1803, ep_reward: 322.1514370298113, ep_step: 1000 +2023-05-26 14:32:03 - SimpleLog - INFO: - episode: 1804, ep_reward: 940.8846236699587, ep_step: 1000 +2023-05-26 14:32:04 - SimpleLog - INFO: - episode: 1805, ep_reward: 473.853276144653, ep_step: 1000 +2023-05-26 14:32:06 - SimpleLog - INFO: - episode: 1806, ep_reward: 315.0112648165894, ep_step: 1000 +2023-05-26 14:32:08 - SimpleLog - INFO: - episode: 1807, ep_reward: 448.38874781493587, ep_step: 1000 +2023-05-26 14:32:10 - SimpleLog - INFO: - episode: 1808, ep_reward: 205.92165281502028, ep_step: 1000 +2023-05-26 14:32:12 - SimpleLog - INFO: - episode: 1809, ep_reward: 374.0248298769058, ep_step: 1000 +2023-05-26 14:32:13 - SimpleLog - INFO: - episode: 1810, ep_reward: 290.44248877244104, ep_step: 1000 +2023-05-26 14:32:15 - SimpleLog - INFO: - episode: 1811, ep_reward: 441.1564951461056, ep_step: 1000 +2023-05-26 14:32:17 - SimpleLog - INFO: - episode: 1812, ep_reward: 324.46703064669083, ep_step: 1000 +2023-05-26 14:32:18 - SimpleLog - INFO: - episode: 1813, ep_reward: 196.42026863609345, ep_step: 1000 +2023-05-26 14:32:20 - SimpleLog - INFO: - episode: 1814, ep_reward: 754.4336261728106, ep_step: 1000 +2023-05-26 14:32:22 - SimpleLog - INFO: - episode: 1815, ep_reward: 333.1766939149631, ep_step: 1000 +2023-05-26 14:32:24 - SimpleLog - INFO: - episode: 1816, ep_reward: 612.136153465028, ep_step: 1000 +2023-05-26 14:32:25 - SimpleLog - INFO: - episode: 1817, ep_reward: 468.2433259030205, ep_step: 1000 +2023-05-26 14:32:27 - SimpleLog - INFO: - episode: 1818, ep_reward: 424.12284155341337, ep_step: 1000 +2023-05-26 14:32:29 - SimpleLog - INFO: - episode: 1819, ep_reward: 804.5934259646176, ep_step: 1000 +2023-05-26 14:32:31 - SimpleLog - INFO: - episode: 1820, ep_reward: 354.3906287682796, ep_step: 1000 +2023-05-26 14:32:33 - SimpleLog - INFO: - episode: 1821, ep_reward: 109.94148341906511, ep_step: 1000 +2023-05-26 14:32:35 - SimpleLog - INFO: - episode: 1822, ep_reward: 429.81221434708664, ep_step: 1000 +2023-05-26 14:32:38 - SimpleLog - INFO: - episode: 1823, ep_reward: 382.8961101342166, ep_step: 1000 +2023-05-26 14:32:39 - SimpleLog - INFO: - episode: 1824, ep_reward: 319.47321723272205, ep_step: 1000 +2023-05-26 14:32:41 - SimpleLog - INFO: - episode: 1825, ep_reward: 325.47944593131217, ep_step: 1000 +2023-05-26 14:32:43 - SimpleLog - INFO: - episode: 1826, ep_reward: 602.730829663677, ep_step: 1000 +2023-05-26 14:32:45 - SimpleLog - INFO: - episode: 1827, ep_reward: 884.9961633586134, ep_step: 1000 +2023-05-26 14:32:46 - SimpleLog - INFO: - episode: 1828, ep_reward: 332.63458146685866, ep_step: 1000 +2023-05-26 14:32:48 - SimpleLog - INFO: - episode: 1829, ep_reward: 272.8174731124806, ep_step: 1000 +2023-05-26 14:32:50 - SimpleLog - INFO: - episode: 1830, ep_reward: 654.9418112386994, ep_step: 1000 +2023-05-26 14:32:51 - SimpleLog - INFO: - episode: 1831, ep_reward: 401.57330820869737, ep_step: 1000 +2023-05-26 14:32:53 - SimpleLog - INFO: - episode: 1832, ep_reward: 247.08565809349156, ep_step: 1000 +2023-05-26 14:32:55 - SimpleLog - INFO: - episode: 1833, ep_reward: 397.3279154183108, ep_step: 1000 +2023-05-26 14:32:56 - SimpleLog - INFO: - episode: 1834, ep_reward: 514.3971364518144, ep_step: 1000 +2023-05-26 14:32:58 - SimpleLog - INFO: - episode: 1835, ep_reward: 330.9890874592991, ep_step: 1000 +2023-05-26 14:33:00 - SimpleLog - INFO: - episode: 1836, ep_reward: 439.7565285322473, ep_step: 1000 +2023-05-26 14:33:01 - SimpleLog - INFO: - episode: 1837, ep_reward: 154.01337833395024, ep_step: 1000 +2023-05-26 14:33:03 - SimpleLog - INFO: - episode: 1838, ep_reward: 547.307969932111, ep_step: 1000 +2023-05-26 14:33:05 - SimpleLog - INFO: - episode: 1839, ep_reward: 462.0130061372408, ep_step: 1000 +2023-05-26 14:33:06 - SimpleLog - INFO: - episode: 1840, ep_reward: 407.8918386676375, ep_step: 1000 +2023-05-26 14:33:08 - SimpleLog - INFO: - episode: 1841, ep_reward: 514.4371611240686, ep_step: 1000 +2023-05-26 14:33:10 - SimpleLog - INFO: - episode: 1842, ep_reward: 310.4517846792338, ep_step: 1000 +2023-05-26 14:33:11 - SimpleLog - INFO: - episode: 1843, ep_reward: 582.0517769279004, ep_step: 1000 +2023-05-26 14:33:13 - SimpleLog - INFO: - episode: 1844, ep_reward: 746.1630141078597, ep_step: 1000 +2023-05-26 14:33:15 - SimpleLog - INFO: - episode: 1845, ep_reward: 365.1522386645089, ep_step: 1000 +2023-05-26 14:33:16 - SimpleLog - INFO: - episode: 1846, ep_reward: 400.8430308763469, ep_step: 1000 +2023-05-26 14:33:18 - SimpleLog - INFO: - episode: 1847, ep_reward: 126.61819083774859, ep_step: 1000 +2023-05-26 14:33:20 - SimpleLog - INFO: - episode: 1848, ep_reward: 319.8634148641182, ep_step: 1000 +2023-05-26 14:33:21 - SimpleLog - INFO: - episode: 1849, ep_reward: 353.5445841104917, ep_step: 1000 +2023-05-26 14:33:23 - SimpleLog - INFO: - episode: 1850, ep_reward: 274.7518048275898, ep_step: 1000 +2023-05-26 14:33:25 - SimpleLog - INFO: - episode: 1851, ep_reward: 176.41290474623668, ep_step: 1000 +2023-05-26 14:33:27 - SimpleLog - INFO: - episode: 1852, ep_reward: 402.5372317980463, ep_step: 1000 +2023-05-26 14:33:28 - SimpleLog - INFO: - episode: 1853, ep_reward: 460.156653101728, ep_step: 1000 +2023-05-26 14:33:30 - SimpleLog - INFO: - episode: 1854, ep_reward: 425.1757115705231, ep_step: 1000 +2023-05-26 14:33:32 - SimpleLog - INFO: - episode: 1855, ep_reward: 651.4697148431475, ep_step: 1000 +2023-05-26 14:33:33 - SimpleLog - INFO: - episode: 1856, ep_reward: 502.6979555927189, ep_step: 1000 +2023-05-26 14:33:35 - SimpleLog - INFO: - episode: 1857, ep_reward: 389.3273810593121, ep_step: 1000 +2023-05-26 14:33:37 - SimpleLog - INFO: - episode: 1858, ep_reward: 448.2074738329478, ep_step: 1000 +2023-05-26 14:33:39 - SimpleLog - INFO: - episode: 1859, ep_reward: 492.3939682577886, ep_step: 1000 +2023-05-26 14:33:40 - SimpleLog - INFO: - episode: 1860, ep_reward: 620.4050533108217, ep_step: 1000 +2023-05-26 14:33:42 - SimpleLog - INFO: - episode: 1861, ep_reward: 476.7908412835444, ep_step: 1000 +2023-05-26 14:33:44 - SimpleLog - INFO: - episode: 1862, ep_reward: 392.40755622082247, ep_step: 1000 +2023-05-26 14:33:46 - SimpleLog - INFO: - episode: 1863, ep_reward: 430.807915873847, ep_step: 1000 +2023-05-26 14:33:48 - SimpleLog - INFO: - episode: 1864, ep_reward: 584.4076559210282, ep_step: 1000 +2023-05-26 14:33:49 - SimpleLog - INFO: - episode: 1865, ep_reward: 478.9877530493087, ep_step: 1000 +2023-05-26 14:33:51 - SimpleLog - INFO: - episode: 1866, ep_reward: 563.977936338644, ep_step: 1000 +2023-05-26 14:33:53 - SimpleLog - INFO: - episode: 1867, ep_reward: 439.2356834344966, ep_step: 1000 +2023-05-26 14:33:54 - SimpleLog - INFO: - episode: 1868, ep_reward: 539.1630241549803, ep_step: 1000 +2023-05-26 14:33:56 - SimpleLog - INFO: - episode: 1869, ep_reward: 531.219474593141, ep_step: 1000 +2023-05-26 14:33:58 - SimpleLog - INFO: - episode: 1870, ep_reward: 151.06990736433238, ep_step: 1000 +2023-05-26 14:33:59 - SimpleLog - INFO: - episode: 1871, ep_reward: 616.1864504565856, ep_step: 1000 +2023-05-26 14:34:01 - SimpleLog - INFO: - episode: 1872, ep_reward: 543.9299863576276, ep_step: 1000 +2023-05-26 14:34:03 - SimpleLog - INFO: - episode: 1873, ep_reward: 585.3285805239344, ep_step: 1000 +2023-05-26 14:34:05 - SimpleLog - INFO: - episode: 1874, ep_reward: 360.3931083334108, ep_step: 1000 +2023-05-26 14:34:06 - SimpleLog - INFO: - episode: 1875, ep_reward: 610.2674596307403, ep_step: 1000 +2023-05-26 14:34:08 - SimpleLog - INFO: - episode: 1876, ep_reward: 536.0575250177161, ep_step: 1000 +2023-05-26 14:34:10 - SimpleLog - INFO: - episode: 1877, ep_reward: 230.14550055739772, ep_step: 1000 +2023-05-26 14:34:11 - SimpleLog - INFO: - episode: 1878, ep_reward: 472.7126840610942, ep_step: 1000 +2023-05-26 14:34:13 - SimpleLog - INFO: - episode: 1879, ep_reward: 305.243540751743, ep_step: 1000 +2023-05-26 14:34:15 - SimpleLog - INFO: - episode: 1880, ep_reward: 681.0197680367926, ep_step: 1000 +2023-05-26 14:34:17 - SimpleLog - INFO: - episode: 1881, ep_reward: 531.6638761269719, ep_step: 1000 +2023-05-26 14:34:18 - SimpleLog - INFO: - episode: 1882, ep_reward: 787.4495569510385, ep_step: 1000 +2023-05-26 14:34:20 - SimpleLog - INFO: - episode: 1883, ep_reward: 365.55838472983277, ep_step: 1000 +2023-05-26 14:34:22 - SimpleLog - INFO: - episode: 1884, ep_reward: 274.0130149255981, ep_step: 1000 +2023-05-26 14:34:23 - SimpleLog - INFO: - episode: 1885, ep_reward: 851.8392199510529, ep_step: 1000 +2023-05-26 14:34:25 - SimpleLog - INFO: - episode: 1886, ep_reward: 392.38248213495046, ep_step: 1000 +2023-05-26 14:34:27 - SimpleLog - INFO: - episode: 1887, ep_reward: 163.671956599601, ep_step: 1000 +2023-05-26 14:34:28 - SimpleLog - INFO: - episode: 1888, ep_reward: 213.67655685897253, ep_step: 1000 +2023-05-26 14:34:30 - SimpleLog - INFO: - episode: 1889, ep_reward: 467.093690384644, ep_step: 1000 +2023-05-26 14:34:32 - SimpleLog - INFO: - episode: 1890, ep_reward: 465.5782151872321, ep_step: 1000 +2023-05-26 14:34:34 - SimpleLog - INFO: - episode: 1891, ep_reward: -224.44180179945516, ep_step: 1000 +2023-05-26 14:34:36 - SimpleLog - INFO: - episode: 1892, ep_reward: 488.3435766526627, ep_step: 1000 +2023-05-26 14:34:37 - SimpleLog - INFO: - episode: 1893, ep_reward: 431.11728849313636, ep_step: 1000 +2023-05-26 14:34:39 - SimpleLog - INFO: - episode: 1894, ep_reward: 306.5992674805834, ep_step: 1000 +2023-05-26 14:34:41 - SimpleLog - INFO: - episode: 1895, ep_reward: 421.20842102020003, ep_step: 1000 +2023-05-26 14:34:42 - SimpleLog - INFO: - episode: 1896, ep_reward: 512.1786589785935, ep_step: 1000 +2023-05-26 14:34:44 - SimpleLog - INFO: - episode: 1897, ep_reward: 486.285443871487, ep_step: 1000 +2023-05-26 14:34:46 - SimpleLog - INFO: - episode: 1898, ep_reward: 647.2572075770843, ep_step: 1000 +2023-05-26 14:34:48 - SimpleLog - INFO: - episode: 1899, ep_reward: 447.967757975583, ep_step: 1000 +2023-05-26 14:34:50 - SimpleLog - INFO: - episode: 1900, ep_reward: 287.08460855113276, ep_step: 1000 +2023-05-26 14:34:52 - SimpleLog - INFO: - episode: 1901, ep_reward: 515.9498950007236, ep_step: 1000 +2023-05-26 14:34:53 - SimpleLog - INFO: - episode: 1902, ep_reward: 353.90776215860535, ep_step: 1000 +2023-05-26 14:34:55 - SimpleLog - INFO: - episode: 1903, ep_reward: 641.6023477925771, ep_step: 1000 +2023-05-26 14:34:57 - SimpleLog - INFO: - episode: 1904, ep_reward: 466.3305614272399, ep_step: 1000 +2023-05-26 14:34:59 - SimpleLog - INFO: - episode: 1905, ep_reward: 460.275638801931, ep_step: 1000 +2023-05-26 14:35:00 - SimpleLog - INFO: - episode: 1906, ep_reward: 107.47542229963507, ep_step: 1000 +2023-05-26 14:35:02 - SimpleLog - INFO: - episode: 1907, ep_reward: 340.53058315164867, ep_step: 1000 +2023-05-26 14:35:04 - SimpleLog - INFO: - episode: 1908, ep_reward: 508.2364493099799, ep_step: 1000 +2023-05-26 14:35:05 - SimpleLog - INFO: - episode: 1909, ep_reward: 597.6628934522364, ep_step: 1000 +2023-05-26 14:35:07 - SimpleLog - INFO: - episode: 1910, ep_reward: 595.1428235061186, ep_step: 1000 +2023-05-26 14:35:09 - SimpleLog - INFO: - episode: 1911, ep_reward: 256.910929979431, ep_step: 1000 +2023-05-26 14:35:11 - SimpleLog - INFO: - episode: 1912, ep_reward: 558.0977270412304, ep_step: 1000 +2023-05-26 14:35:12 - SimpleLog - INFO: - episode: 1913, ep_reward: 589.2104552446773, ep_step: 1000 +2023-05-26 14:35:14 - SimpleLog - INFO: - episode: 1914, ep_reward: 560.9589877805626, ep_step: 1000 +2023-05-26 14:35:16 - SimpleLog - INFO: - episode: 1915, ep_reward: 186.1051181940998, ep_step: 1000 +2023-05-26 14:35:17 - SimpleLog - INFO: - episode: 1916, ep_reward: 650.8150387390541, ep_step: 1000 +2023-05-26 14:35:19 - SimpleLog - INFO: - episode: 1917, ep_reward: 590.998097560756, ep_step: 1000 +2023-05-26 14:35:21 - SimpleLog - INFO: - episode: 1918, ep_reward: 442.80767101480666, ep_step: 1000 +2023-05-26 14:35:28 - SimpleLog - INFO: - update_step: 7500, online_eval_reward: 683.742 +2023-05-26 14:35:28 - SimpleLog - INFO: - episode: 1919, ep_reward: 492.27310587095803, ep_step: 1000 +2023-05-26 14:35:29 - SimpleLog - INFO: - episode: 1920, ep_reward: 108.34980775214905, ep_step: 1000 +2023-05-26 14:35:30 - SimpleLog - INFO: - episode: 1921, ep_reward: 491.614843939276, ep_step: 1000 +2023-05-26 14:35:31 - SimpleLog - INFO: - episode: 1922, ep_reward: 496.77094098093124, ep_step: 1000 +2023-05-26 14:35:33 - SimpleLog - INFO: - episode: 1923, ep_reward: 298.100455324843, ep_step: 1000 +2023-05-26 14:35:34 - SimpleLog - INFO: - episode: 1924, ep_reward: 502.2923565168821, ep_step: 1000 +2023-05-26 14:35:35 - SimpleLog - INFO: - episode: 1925, ep_reward: 508.90772195483197, ep_step: 1000 +2023-05-26 14:35:37 - SimpleLog - INFO: - episode: 1926, ep_reward: 89.24702383083932, ep_step: 1000 +2023-05-26 14:35:38 - SimpleLog - INFO: - episode: 1927, ep_reward: 615.3747858233775, ep_step: 1000 +2023-05-26 14:35:40 - SimpleLog - INFO: - episode: 1928, ep_reward: 464.49279625635575, ep_step: 1000 +2023-05-26 14:35:42 - SimpleLog - INFO: - episode: 1929, ep_reward: -30.89137788996994, ep_step: 1000 +2023-05-26 14:35:43 - SimpleLog - INFO: - episode: 1930, ep_reward: 305.36128865145594, ep_step: 1000 +2023-05-26 14:35:45 - SimpleLog - INFO: - episode: 1931, ep_reward: 431.2404595399731, ep_step: 1000 +2023-05-26 14:35:47 - SimpleLog - INFO: - episode: 1932, ep_reward: 551.386757764259, ep_step: 1000 +2023-05-26 14:35:48 - SimpleLog - INFO: - episode: 1933, ep_reward: 520.1652622115847, ep_step: 1000 +2023-05-26 14:35:50 - SimpleLog - INFO: - episode: 1934, ep_reward: 492.71735752733167, ep_step: 1000 +2023-05-26 14:35:52 - SimpleLog - INFO: - episode: 1935, ep_reward: 311.07114128870955, ep_step: 1000 +2023-05-26 14:35:54 - SimpleLog - INFO: - episode: 1936, ep_reward: 701.1909963822977, ep_step: 1000 +2023-05-26 14:35:57 - SimpleLog - INFO: - episode: 1937, ep_reward: 482.66506906612005, ep_step: 1000 +2023-05-26 14:35:58 - SimpleLog - INFO: - episode: 1938, ep_reward: 584.017835648933, ep_step: 1000 +2023-05-26 14:36:00 - SimpleLog - INFO: - episode: 1939, ep_reward: 229.9836526599404, ep_step: 1000 +2023-05-26 14:36:02 - SimpleLog - INFO: - episode: 1940, ep_reward: 519.5801658201307, ep_step: 1000 +2023-05-26 14:36:03 - SimpleLog - INFO: - episode: 1941, ep_reward: 569.4621977909454, ep_step: 1000 +2023-05-26 14:36:05 - SimpleLog - INFO: - episode: 1942, ep_reward: 345.83323629402855, ep_step: 1000 +2023-05-26 14:36:07 - SimpleLog - INFO: - episode: 1943, ep_reward: 399.57722180312606, ep_step: 1000 +2023-05-26 14:36:09 - SimpleLog - INFO: - episode: 1944, ep_reward: 195.77130108496056, ep_step: 1000 +2023-05-26 14:36:10 - SimpleLog - INFO: - episode: 1945, ep_reward: 504.99043417419847, ep_step: 1000 +2023-05-26 14:36:12 - SimpleLog - INFO: - episode: 1946, ep_reward: 289.02736354047914, ep_step: 1000 +2023-05-26 14:36:14 - SimpleLog - INFO: - episode: 1947, ep_reward: 532.7710872974176, ep_step: 1000 +2023-05-26 14:36:15 - SimpleLog - INFO: - episode: 1948, ep_reward: 591.1374710302049, ep_step: 1000 +2023-05-26 14:36:17 - SimpleLog - INFO: - episode: 1949, ep_reward: 467.02224037718446, ep_step: 1000 +2023-05-26 14:36:19 - SimpleLog - INFO: - episode: 1950, ep_reward: 506.0524081882857, ep_step: 1000 +2023-05-26 14:36:20 - SimpleLog - INFO: - episode: 1951, ep_reward: 337.2509155566187, ep_step: 1000 +2023-05-26 14:36:22 - SimpleLog - INFO: - episode: 1952, ep_reward: 254.44668750784302, ep_step: 1000 +2023-05-26 14:36:24 - SimpleLog - INFO: - episode: 1953, ep_reward: 533.2439300869726, ep_step: 1000 +2023-05-26 14:36:25 - SimpleLog - INFO: - episode: 1954, ep_reward: 558.7975618697249, ep_step: 1000 +2023-05-26 14:36:27 - SimpleLog - INFO: - episode: 1955, ep_reward: 493.74712018263926, ep_step: 1000 +2023-05-26 14:36:29 - SimpleLog - INFO: - episode: 1956, ep_reward: 451.3200641101535, ep_step: 1000 +2023-05-26 14:36:31 - SimpleLog - INFO: - episode: 1957, ep_reward: -308.4835536851063, ep_step: 1000 +2023-05-26 14:36:33 - SimpleLog - INFO: - episode: 1958, ep_reward: 371.03419362300804, ep_step: 1000 +2023-05-26 14:36:34 - SimpleLog - INFO: - episode: 1959, ep_reward: 514.8988856359239, ep_step: 1000 +2023-05-26 14:36:36 - SimpleLog - INFO: - episode: 1960, ep_reward: 314.8077188569651, ep_step: 1000 +2023-05-26 14:36:38 - SimpleLog - INFO: - episode: 1961, ep_reward: 421.03697626564394, ep_step: 1000 +2023-05-26 14:36:40 - SimpleLog - INFO: - episode: 1962, ep_reward: 454.18719212478146, ep_step: 1000 +2023-05-26 14:36:42 - SimpleLog - INFO: - episode: 1963, ep_reward: 314.9735901247696, ep_step: 1000 +2023-05-26 14:36:43 - SimpleLog - INFO: - episode: 1964, ep_reward: 484.7778319643111, ep_step: 1000 +2023-05-26 14:36:45 - SimpleLog - INFO: - episode: 1965, ep_reward: 399.818833621201, ep_step: 1000 +2023-05-26 14:36:47 - SimpleLog - INFO: - episode: 1966, ep_reward: 425.40220209845285, ep_step: 1000 +2023-05-26 14:36:49 - SimpleLog - INFO: - episode: 1967, ep_reward: 491.2387590750066, ep_step: 1000 +2023-05-26 14:36:50 - SimpleLog - INFO: - episode: 1968, ep_reward: 434.6640210779768, ep_step: 1000 +2023-05-26 14:36:52 - SimpleLog - INFO: - episode: 1969, ep_reward: 421.50248949716405, ep_step: 1000 +2023-05-26 14:36:54 - SimpleLog - INFO: - episode: 1970, ep_reward: 500.5855109903923, ep_step: 1000 +2023-05-26 14:36:55 - SimpleLog - INFO: - episode: 1971, ep_reward: 525.6190129726306, ep_step: 1000 +2023-05-26 14:36:57 - SimpleLog - INFO: - episode: 1972, ep_reward: 694.7826825854827, ep_step: 1000 +2023-05-26 14:36:59 - SimpleLog - INFO: - episode: 1973, ep_reward: 348.11084557118346, ep_step: 1000 +2023-05-26 14:37:01 - SimpleLog - INFO: - episode: 1974, ep_reward: 548.5685081053855, ep_step: 1000 +2023-05-26 14:37:03 - SimpleLog - INFO: - episode: 1975, ep_reward: 435.4791647979025, ep_step: 1000 +2023-05-26 14:37:05 - SimpleLog - INFO: - episode: 1976, ep_reward: 96.16766261594739, ep_step: 1000 +2023-05-26 14:37:07 - SimpleLog - INFO: - episode: 1977, ep_reward: 154.7844952240069, ep_step: 1000 +2023-05-26 14:37:08 - SimpleLog - INFO: - episode: 1978, ep_reward: 459.9139922841727, ep_step: 1000 +2023-05-26 14:37:10 - SimpleLog - INFO: - episode: 1979, ep_reward: 426.2366762581665, ep_step: 1000 +2023-05-26 14:37:12 - SimpleLog - INFO: - episode: 1980, ep_reward: 535.43602552388, ep_step: 1000 +2023-05-26 14:37:13 - SimpleLog - INFO: - episode: 1981, ep_reward: 520.9284382841151, ep_step: 1000 +2023-05-26 14:37:15 - SimpleLog - INFO: - episode: 1982, ep_reward: 498.9086144480566, ep_step: 1000 +2023-05-26 14:37:17 - SimpleLog - INFO: - episode: 1983, ep_reward: 659.4156578583612, ep_step: 1000 +2023-05-26 14:37:18 - SimpleLog - INFO: - episode: 1984, ep_reward: 660.4096318296658, ep_step: 1000 +2023-05-26 14:37:20 - SimpleLog - INFO: - episode: 1985, ep_reward: 75.33051354543494, ep_step: 1000 +2023-05-26 14:37:22 - SimpleLog - INFO: - episode: 1986, ep_reward: 511.522687241474, ep_step: 1000 +2023-05-26 14:37:24 - SimpleLog - INFO: - episode: 1987, ep_reward: 0.02243072218278641, ep_step: 1000 +2023-05-26 14:37:25 - SimpleLog - INFO: - episode: 1988, ep_reward: 381.47370404596296, ep_step: 1000 +2023-05-26 14:37:27 - SimpleLog - INFO: - episode: 1989, ep_reward: 441.27144611082457, ep_step: 1000 +2023-05-26 14:37:29 - SimpleLog - INFO: - episode: 1990, ep_reward: 472.2867066739995, ep_step: 1000 +2023-05-26 14:37:31 - SimpleLog - INFO: - episode: 1991, ep_reward: 509.2418607880765, ep_step: 1000 +2023-05-26 14:37:33 - SimpleLog - INFO: - episode: 1992, ep_reward: 455.2988639994149, ep_step: 1000 +2023-05-26 14:37:34 - SimpleLog - INFO: - episode: 1993, ep_reward: 576.2563483402614, ep_step: 1000 +2023-05-26 14:37:36 - SimpleLog - INFO: - episode: 1994, ep_reward: 470.5053723584194, ep_step: 1000 +2023-05-26 14:37:38 - SimpleLog - INFO: - episode: 1995, ep_reward: 529.5970654603547, ep_step: 1000 +2023-05-26 14:37:40 - SimpleLog - INFO: - episode: 1996, ep_reward: 490.99630938225283, ep_step: 1000 +2023-05-26 14:37:41 - SimpleLog - INFO: - episode: 1997, ep_reward: 425.49298735678485, ep_step: 1000 +2023-05-26 14:37:43 - SimpleLog - INFO: - episode: 1998, ep_reward: 204.31755899213059, ep_step: 1000 +2023-05-26 14:37:45 - SimpleLog - INFO: - episode: 1999, ep_reward: 474.9879095264208, ep_step: 1000 +2023-05-26 14:37:45 - SimpleLog - INFO: - Finish training! total time consumed: 3806.64s