Train_Pendulum-v1_A2C
#11
by
gsc579
- opened
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/config.yaml +56 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/logs/log.txt +603 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/10 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/100 +3 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/110 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/120 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/130 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/140 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/150 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/160 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/170 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/180 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/190 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/20 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/200 +3 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/210 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/220 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/230 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/240 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/250 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/260 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/270 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/280 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/290 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/30 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/300 +3 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/310 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/320 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/330 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/340 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/350 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/360 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/370 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/380 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/390 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/40 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/50 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/60 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/70 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/80 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/90 +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/best +0 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/tb_logs/interact/events.out.tfevents.1687534112.ML3090.1059326.0 +3 -0
- ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/tb_logs/policy/events.out.tfevents.1687534112.ML3090.1059326.1 +3 -0
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/config.yaml
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
general_cfg:
|
2 |
+
algo_name: A2C
|
3 |
+
collect_traj: false
|
4 |
+
device: cpu
|
5 |
+
env_name: gym
|
6 |
+
interact_summary_fre: 1
|
7 |
+
load_checkpoint: false
|
8 |
+
load_model_step: best
|
9 |
+
load_path: Train_single_CartPole-v1_DQN_20230515-211721
|
10 |
+
max_episode: 500
|
11 |
+
max_step: 200
|
12 |
+
mode: train
|
13 |
+
model_save_fre: 10
|
14 |
+
model_summary_fre: 1
|
15 |
+
mp_backend: single
|
16 |
+
n_learners: 1
|
17 |
+
n_workers: 2
|
18 |
+
online_eval: true
|
19 |
+
online_eval_episode: 10
|
20 |
+
seed: 1
|
21 |
+
share_buffer: true
|
22 |
+
algo_cfg:
|
23 |
+
action_type: continuous
|
24 |
+
actor_hidden_dim: 256
|
25 |
+
actor_layers:
|
26 |
+
- activation: relu
|
27 |
+
layer_size:
|
28 |
+
- 256
|
29 |
+
layer_type: linear
|
30 |
+
actor_lr: 0.0001
|
31 |
+
batch_size: 256
|
32 |
+
buffer_type: ONPOLICY_QUE
|
33 |
+
critic_hidden_dim: 256
|
34 |
+
critic_layers:
|
35 |
+
- activation: relu
|
36 |
+
layer_size:
|
37 |
+
- 256
|
38 |
+
layer_type: linear
|
39 |
+
critic_loss_coef: 0.5
|
40 |
+
critic_lr: 0.005
|
41 |
+
entropy_coef: 0.01
|
42 |
+
gamma: 0.9
|
43 |
+
independ_actor: true
|
44 |
+
k_epochs: 4
|
45 |
+
lr: 0.0001
|
46 |
+
min_policy: 0
|
47 |
+
n_steps_per_learn: 1
|
48 |
+
sgd_batch_size: 32
|
49 |
+
share_optimizer: false
|
50 |
+
env_cfg:
|
51 |
+
id: Pendulum-v1
|
52 |
+
ignore_params:
|
53 |
+
- wrapper
|
54 |
+
- ignore_params
|
55 |
+
render_mode: null
|
56 |
+
wrapper: null
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/logs/log.txt
ADDED
@@ -0,0 +1,603 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - General Configs:
|
2 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - ================================================================================
|
3 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - Name Value Type
|
4 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - env_name gym <class 'str'>
|
5 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - algo_name A2C <class 'str'>
|
6 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - mode train <class 'str'>
|
7 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - device cpu <class 'str'>
|
8 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - seed 1 <class 'int'>
|
9 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - max_episode 500 <class 'int'>
|
10 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - max_step 200 <class 'int'>
|
11 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
|
12 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - mp_backend single <class 'str'>
|
13 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - n_workers 2 <class 'int'>
|
14 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - n_learners 1 <class 'int'>
|
15 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
|
16 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
|
17 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'>
|
18 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - model_save_fre 10 <class 'int'>
|
19 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - load_checkpoint 0 <class 'bool'>
|
20 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_DQN_20230515-211721 <class 'str'>
|
21 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - load_model_step best <class 'str'>
|
22 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - interact_summary_fre 1 <class 'int'>
|
23 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - model_summary_fre 1 <class 'int'>
|
24 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - ================================================================================
|
25 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - Algo Configs:
|
26 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - ================================================================================
|
27 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - Name Value Type
|
28 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - independ_actor 1 <class 'bool'>
|
29 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - share_optimizer 0 <class 'bool'>
|
30 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - action_type continuous <class 'str'>
|
31 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - gamma 0.9 <class 'float'>
|
32 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - k_epochs 4 <class 'int'>
|
33 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - lr 0.0001 <class 'float'>
|
34 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - actor_lr 0.0001 <class 'float'>
|
35 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - critic_lr 0.005 <class 'float'>
|
36 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - critic_loss_coef 0.5 <class 'float'>
|
37 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - entropy_coef 0.01 <class 'float'>
|
38 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - buffer_type ONPOLICY_QUE <class 'str'>
|
39 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - batch_size 256 <class 'int'>
|
40 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - sgd_batch_size 32 <class 'int'>
|
41 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - actor_hidden_dim 256 <class 'int'>
|
42 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - critic_hidden_dim 256 <class 'int'>
|
43 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - min_policy 0 <class 'int'>
|
44 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - n_steps_per_learn 1 <class 'int'>
|
45 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
|
46 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
|
47 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - ================================================================================
|
48 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - Env Configs:
|
49 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - ================================================================================
|
50 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - Name Value Type
|
51 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - id Pendulum-v1 <class 'str'>
|
52 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - render_mode None <class 'str'>
|
53 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - wrapper None <class 'str'>
|
54 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
|
55 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - ================================================================================
|
56 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - Start training!
|
57 |
+
2023-06-23 23:28:32 - SimpleLog - INFO: - Interactor 0 finished episode 1 with reward -900.837 in 200 steps
|
58 |
+
2023-06-23 23:28:33 - SimpleLog - INFO: - Interactor 1 finished episode 2 with reward -1437.596 in 200 steps
|
59 |
+
2023-06-23 23:28:33 - SimpleLog - INFO: - Interactor 0 finished episode 3 with reward -1001.312 in 200 steps
|
60 |
+
2023-06-23 23:28:33 - SimpleLog - INFO: - Interactor 1 finished episode 4 with reward -1507.537 in 200 steps
|
61 |
+
2023-06-23 23:28:33 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward -1347.798 in 200 steps
|
62 |
+
2023-06-23 23:28:33 - SimpleLog - INFO: - Interactor 1 finished episode 6 with reward -1512.501 in 200 steps
|
63 |
+
2023-06-23 23:28:34 - SimpleLog - INFO: - Interactor 0 finished episode 7 with reward -1208.837 in 200 steps
|
64 |
+
2023-06-23 23:28:34 - SimpleLog - INFO: - Interactor 0 finished episode 8 with reward -899.205 in 200 steps
|
65 |
+
2023-06-23 23:28:34 - SimpleLog - INFO: - Interactor 1 finished episode 9 with reward -1406.472 in 200 steps
|
66 |
+
2023-06-23 23:28:34 - SimpleLog - INFO: - Interactor 1 finished episode 10 with reward -1200.804 in 200 steps
|
67 |
+
2023-06-23 23:28:34 - SimpleLog - INFO: - Interactor 0 finished episode 11 with reward -872.005 in 200 steps
|
68 |
+
2023-06-23 23:28:34 - SimpleLog - INFO: - Interactor 1 finished episode 12 with reward -1176.206 in 200 steps
|
69 |
+
2023-06-23 23:28:35 - SimpleLog - INFO: - update_step: 10, online_eval_reward: -899.427
|
70 |
+
2023-06-23 23:28:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -899.427, save the best model!
|
71 |
+
2023-06-23 23:28:35 - SimpleLog - INFO: - Interactor 0 finished episode 13 with reward -902.914 in 200 steps
|
72 |
+
2023-06-23 23:28:35 - SimpleLog - INFO: - Interactor 1 finished episode 14 with reward -983.850 in 200 steps
|
73 |
+
2023-06-23 23:28:35 - SimpleLog - INFO: - Interactor 0 finished episode 15 with reward -1026.852 in 200 steps
|
74 |
+
2023-06-23 23:28:35 - SimpleLog - INFO: - Interactor 1 finished episode 16 with reward -994.666 in 200 steps
|
75 |
+
2023-06-23 23:28:35 - SimpleLog - INFO: - Interactor 0 finished episode 17 with reward -1296.251 in 200 steps
|
76 |
+
2023-06-23 23:28:36 - SimpleLog - INFO: - Interactor 0 finished episode 18 with reward -1380.217 in 200 steps
|
77 |
+
2023-06-23 23:28:36 - SimpleLog - INFO: - Interactor 1 finished episode 19 with reward -1409.424 in 200 steps
|
78 |
+
2023-06-23 23:28:36 - SimpleLog - INFO: - Interactor 1 finished episode 20 with reward -1505.479 in 200 steps
|
79 |
+
2023-06-23 23:28:36 - SimpleLog - INFO: - Interactor 0 finished episode 21 with reward -1212.614 in 200 steps
|
80 |
+
2023-06-23 23:28:36 - SimpleLog - INFO: - Interactor 1 finished episode 22 with reward -1418.450 in 200 steps
|
81 |
+
2023-06-23 23:28:36 - SimpleLog - INFO: - Interactor 0 finished episode 23 with reward -1177.955 in 200 steps
|
82 |
+
2023-06-23 23:28:36 - SimpleLog - INFO: - Interactor 1 finished episode 24 with reward -1219.158 in 200 steps
|
83 |
+
2023-06-23 23:28:37 - SimpleLog - INFO: - update_step: 20, online_eval_reward: -875.567
|
84 |
+
2023-06-23 23:28:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -875.567, save the best model!
|
85 |
+
2023-06-23 23:28:37 - SimpleLog - INFO: - Interactor 0 finished episode 25 with reward -842.990 in 200 steps
|
86 |
+
2023-06-23 23:28:37 - SimpleLog - INFO: - Interactor 0 finished episode 26 with reward -755.918 in 200 steps
|
87 |
+
2023-06-23 23:28:37 - SimpleLog - INFO: - Interactor 1 finished episode 27 with reward -1160.682 in 200 steps
|
88 |
+
2023-06-23 23:28:37 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward -854.279 in 200 steps
|
89 |
+
2023-06-23 23:28:37 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward -1070.616 in 200 steps
|
90 |
+
2023-06-23 23:28:38 - SimpleLog - INFO: - Interactor 1 finished episode 30 with reward -1086.192 in 200 steps
|
91 |
+
2023-06-23 23:28:38 - SimpleLog - INFO: - Interactor 0 finished episode 31 with reward -1025.180 in 200 steps
|
92 |
+
2023-06-23 23:28:38 - SimpleLog - INFO: - Interactor 1 finished episode 32 with reward -984.032 in 200 steps
|
93 |
+
2023-06-23 23:28:38 - SimpleLog - INFO: - Interactor 0 finished episode 33 with reward -923.790 in 200 steps
|
94 |
+
2023-06-23 23:28:38 - SimpleLog - INFO: - Interactor 1 finished episode 34 with reward -1137.494 in 200 steps
|
95 |
+
2023-06-23 23:28:39 - SimpleLog - INFO: - Interactor 0 finished episode 35 with reward -1346.876 in 200 steps
|
96 |
+
2023-06-23 23:28:39 - SimpleLog - INFO: - Interactor 0 finished episode 36 with reward -905.609 in 200 steps
|
97 |
+
2023-06-23 23:28:39 - SimpleLog - INFO: - Interactor 1 finished episode 37 with reward -1044.164 in 200 steps
|
98 |
+
2023-06-23 23:28:39 - SimpleLog - INFO: - Interactor 1 finished episode 38 with reward -970.728 in 200 steps
|
99 |
+
2023-06-23 23:28:39 - SimpleLog - INFO: - update_step: 30, online_eval_reward: -1070.422
|
100 |
+
2023-06-23 23:28:39 - SimpleLog - INFO: - Interactor 0 finished episode 39 with reward -1032.134 in 200 steps
|
101 |
+
2023-06-23 23:28:40 - SimpleLog - INFO: - Interactor 1 finished episode 40 with reward -1121.969 in 200 steps
|
102 |
+
2023-06-23 23:28:40 - SimpleLog - INFO: - Interactor 0 finished episode 41 with reward -1234.077 in 200 steps
|
103 |
+
2023-06-23 23:28:40 - SimpleLog - INFO: - Interactor 1 finished episode 42 with reward -1206.985 in 200 steps
|
104 |
+
2023-06-23 23:28:40 - SimpleLog - INFO: - Interactor 0 finished episode 43 with reward -1049.248 in 200 steps
|
105 |
+
2023-06-23 23:28:40 - SimpleLog - INFO: - Interactor 0 finished episode 44 with reward -1217.191 in 200 steps
|
106 |
+
2023-06-23 23:28:40 - SimpleLog - INFO: - Interactor 1 finished episode 45 with reward -1232.860 in 200 steps
|
107 |
+
2023-06-23 23:28:40 - SimpleLog - INFO: - Interactor 1 finished episode 46 with reward -1181.447 in 200 steps
|
108 |
+
2023-06-23 23:28:41 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward -1246.829 in 200 steps
|
109 |
+
2023-06-23 23:28:41 - SimpleLog - INFO: - Interactor 1 finished episode 48 with reward -1331.505 in 200 steps
|
110 |
+
2023-06-23 23:28:41 - SimpleLog - INFO: - Interactor 0 finished episode 49 with reward -1044.725 in 200 steps
|
111 |
+
2023-06-23 23:28:41 - SimpleLog - INFO: - Interactor 1 finished episode 50 with reward -1205.135 in 200 steps
|
112 |
+
2023-06-23 23:28:42 - SimpleLog - INFO: - update_step: 40, online_eval_reward: -933.384
|
113 |
+
2023-06-23 23:28:42 - SimpleLog - INFO: - Interactor 0 finished episode 51 with reward -1314.521 in 200 steps
|
114 |
+
2023-06-23 23:28:42 - SimpleLog - INFO: - Interactor 1 finished episode 52 with reward -1188.421 in 200 steps
|
115 |
+
2023-06-23 23:28:42 - SimpleLog - INFO: - Interactor 0 finished episode 53 with reward -951.084 in 200 steps
|
116 |
+
2023-06-23 23:28:42 - SimpleLog - INFO: - Interactor 0 finished episode 54 with reward -1321.350 in 200 steps
|
117 |
+
2023-06-23 23:28:42 - SimpleLog - INFO: - Interactor 1 finished episode 55 with reward -1174.556 in 200 steps
|
118 |
+
2023-06-23 23:28:42 - SimpleLog - INFO: - Interactor 1 finished episode 56 with reward -1283.907 in 200 steps
|
119 |
+
2023-06-23 23:28:43 - SimpleLog - INFO: - Interactor 0 finished episode 57 with reward -1104.791 in 200 steps
|
120 |
+
2023-06-23 23:28:43 - SimpleLog - INFO: - Interactor 1 finished episode 58 with reward -1351.203 in 200 steps
|
121 |
+
2023-06-23 23:28:43 - SimpleLog - INFO: - Interactor 0 finished episode 59 with reward -1097.175 in 200 steps
|
122 |
+
2023-06-23 23:28:43 - SimpleLog - INFO: - Interactor 1 finished episode 60 with reward -1221.793 in 200 steps
|
123 |
+
2023-06-23 23:28:43 - SimpleLog - INFO: - Interactor 0 finished episode 61 with reward -1187.994 in 200 steps
|
124 |
+
2023-06-23 23:28:43 - SimpleLog - INFO: - Interactor 0 finished episode 62 with reward -1080.992 in 200 steps
|
125 |
+
2023-06-23 23:28:43 - SimpleLog - INFO: - Interactor 1 finished episode 63 with reward -978.285 in 200 steps
|
126 |
+
2023-06-23 23:28:43 - SimpleLog - INFO: - Interactor 1 finished episode 64 with reward -1233.243 in 200 steps
|
127 |
+
2023-06-23 23:28:44 - SimpleLog - INFO: - update_step: 50, online_eval_reward: -996.494
|
128 |
+
2023-06-23 23:28:44 - SimpleLog - INFO: - Interactor 0 finished episode 65 with reward -983.907 in 200 steps
|
129 |
+
2023-06-23 23:28:44 - SimpleLog - INFO: - Interactor 1 finished episode 66 with reward -859.202 in 200 steps
|
130 |
+
2023-06-23 23:28:44 - SimpleLog - INFO: - Interactor 0 finished episode 67 with reward -969.270 in 200 steps
|
131 |
+
2023-06-23 23:28:45 - SimpleLog - INFO: - Interactor 1 finished episode 68 with reward -1052.834 in 200 steps
|
132 |
+
2023-06-23 23:28:45 - SimpleLog - INFO: - Interactor 0 finished episode 69 with reward -1052.915 in 200 steps
|
133 |
+
2023-06-23 23:28:45 - SimpleLog - INFO: - Interactor 1 finished episode 70 with reward -991.591 in 200 steps
|
134 |
+
2023-06-23 23:28:45 - SimpleLog - INFO: - Interactor 0 finished episode 71 with reward -1201.288 in 200 steps
|
135 |
+
2023-06-23 23:28:45 - SimpleLog - INFO: - Interactor 0 finished episode 72 with reward -1229.202 in 200 steps
|
136 |
+
2023-06-23 23:28:45 - SimpleLog - INFO: - Interactor 1 finished episode 73 with reward -1111.154 in 200 steps
|
137 |
+
2023-06-23 23:28:45 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward -1418.303 in 200 steps
|
138 |
+
2023-06-23 23:28:46 - SimpleLog - INFO: - Interactor 0 finished episode 75 with reward -1151.437 in 200 steps
|
139 |
+
2023-06-23 23:28:46 - SimpleLog - INFO: - Interactor 1 finished episode 76 with reward -1267.621 in 200 steps
|
140 |
+
2023-06-23 23:28:46 - SimpleLog - INFO: - update_step: 60, online_eval_reward: -1097.994
|
141 |
+
2023-06-23 23:28:46 - SimpleLog - INFO: - Interactor 0 finished episode 77 with reward -1109.193 in 200 steps
|
142 |
+
2023-06-23 23:28:46 - SimpleLog - INFO: - Interactor 1 finished episode 78 with reward -1261.967 in 200 steps
|
143 |
+
2023-06-23 23:28:47 - SimpleLog - INFO: - Interactor 0 finished episode 79 with reward -1114.276 in 200 steps
|
144 |
+
2023-06-23 23:28:47 - SimpleLog - INFO: - Interactor 1 finished episode 80 with reward -1216.767 in 200 steps
|
145 |
+
2023-06-23 23:28:47 - SimpleLog - INFO: - Interactor 0 finished episode 81 with reward -1131.662 in 200 steps
|
146 |
+
2023-06-23 23:28:47 - SimpleLog - INFO: - Interactor 0 finished episode 82 with reward -1080.096 in 200 steps
|
147 |
+
2023-06-23 23:28:47 - SimpleLog - INFO: - Interactor 1 finished episode 83 with reward -1243.884 in 200 steps
|
148 |
+
2023-06-23 23:28:47 - SimpleLog - INFO: - Interactor 1 finished episode 84 with reward -1106.985 in 200 steps
|
149 |
+
2023-06-23 23:28:48 - SimpleLog - INFO: - Interactor 0 finished episode 85 with reward -1100.087 in 200 steps
|
150 |
+
2023-06-23 23:28:48 - SimpleLog - INFO: - Interactor 1 finished episode 86 with reward -1317.505 in 200 steps
|
151 |
+
2023-06-23 23:28:48 - SimpleLog - INFO: - Interactor 0 finished episode 87 with reward -1002.401 in 200 steps
|
152 |
+
2023-06-23 23:28:48 - SimpleLog - INFO: - Interactor 1 finished episode 88 with reward -1117.220 in 200 steps
|
153 |
+
2023-06-23 23:28:49 - SimpleLog - INFO: - update_step: 70, online_eval_reward: -829.047
|
154 |
+
2023-06-23 23:28:49 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -829.047, save the best model!
|
155 |
+
2023-06-23 23:28:49 - SimpleLog - INFO: - Interactor 0 finished episode 89 with reward -978.134 in 200 steps
|
156 |
+
2023-06-23 23:28:49 - SimpleLog - INFO: - Interactor 0 finished episode 90 with reward -920.231 in 200 steps
|
157 |
+
2023-06-23 23:28:49 - SimpleLog - INFO: - Interactor 1 finished episode 91 with reward -1102.727 in 200 steps
|
158 |
+
2023-06-23 23:28:49 - SimpleLog - INFO: - Interactor 1 finished episode 92 with reward -880.569 in 200 steps
|
159 |
+
2023-06-23 23:28:49 - SimpleLog - INFO: - Interactor 0 finished episode 93 with reward -977.822 in 200 steps
|
160 |
+
2023-06-23 23:28:49 - SimpleLog - INFO: - Interactor 1 finished episode 94 with reward -1027.876 in 200 steps
|
161 |
+
2023-06-23 23:28:49 - SimpleLog - INFO: - Interactor 0 finished episode 95 with reward -1057.179 in 200 steps
|
162 |
+
2023-06-23 23:28:50 - SimpleLog - INFO: - Interactor 1 finished episode 96 with reward -1181.590 in 200 steps
|
163 |
+
2023-06-23 23:28:50 - SimpleLog - INFO: - Interactor 0 finished episode 97 with reward -1088.957 in 200 steps
|
164 |
+
2023-06-23 23:28:50 - SimpleLog - INFO: - Interactor 1 finished episode 98 with reward -1121.544 in 200 steps
|
165 |
+
2023-06-23 23:28:50 - SimpleLog - INFO: - Interactor 0 finished episode 99 with reward -800.585 in 200 steps
|
166 |
+
2023-06-23 23:28:50 - SimpleLog - INFO: - Interactor 0 finished episode 100 with reward -1075.582 in 200 steps
|
167 |
+
2023-06-23 23:28:50 - SimpleLog - INFO: - Interactor 1 finished episode 101 with reward -984.790 in 200 steps
|
168 |
+
2023-06-23 23:28:50 - SimpleLog - INFO: - Interactor 1 finished episode 102 with reward -1099.587 in 200 steps
|
169 |
+
2023-06-23 23:28:51 - SimpleLog - INFO: - update_step: 80, online_eval_reward: -822.131
|
170 |
+
2023-06-23 23:28:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -822.131, save the best model!
|
171 |
+
2023-06-23 23:28:51 - SimpleLog - INFO: - Interactor 0 finished episode 103 with reward -945.995 in 200 steps
|
172 |
+
2023-06-23 23:28:51 - SimpleLog - INFO: - Interactor 1 finished episode 104 with reward -887.473 in 200 steps
|
173 |
+
2023-06-23 23:28:51 - SimpleLog - INFO: - Interactor 0 finished episode 105 with reward -1057.001 in 200 steps
|
174 |
+
2023-06-23 23:28:51 - SimpleLog - INFO: - Interactor 1 finished episode 106 with reward -977.805 in 200 steps
|
175 |
+
2023-06-23 23:28:52 - SimpleLog - INFO: - Interactor 0 finished episode 107 with reward -1012.345 in 200 steps
|
176 |
+
2023-06-23 23:28:52 - SimpleLog - INFO: - Interactor 0 finished episode 108 with reward -988.798 in 200 steps
|
177 |
+
2023-06-23 23:28:52 - SimpleLog - INFO: - Interactor 1 finished episode 109 with reward -1004.900 in 200 steps
|
178 |
+
2023-06-23 23:28:52 - SimpleLog - INFO: - Interactor 1 finished episode 110 with reward -1173.580 in 200 steps
|
179 |
+
2023-06-23 23:28:52 - SimpleLog - INFO: - Interactor 0 finished episode 111 with reward -865.416 in 200 steps
|
180 |
+
2023-06-23 23:28:52 - SimpleLog - INFO: - Interactor 1 finished episode 112 with reward -1164.669 in 200 steps
|
181 |
+
2023-06-23 23:28:53 - SimpleLog - INFO: - Interactor 0 finished episode 113 with reward -905.671 in 200 steps
|
182 |
+
2023-06-23 23:28:53 - SimpleLog - INFO: - Interactor 1 finished episode 114 with reward -1004.813 in 200 steps
|
183 |
+
2023-06-23 23:28:53 - SimpleLog - INFO: - update_step: 90, online_eval_reward: -634.393
|
184 |
+
2023-06-23 23:28:53 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -634.393, save the best model!
|
185 |
+
2023-06-23 23:28:53 - SimpleLog - INFO: - Interactor 0 finished episode 115 with reward -875.029 in 200 steps
|
186 |
+
2023-06-23 23:28:53 - SimpleLog - INFO: - Interactor 1 finished episode 116 with reward -994.775 in 200 steps
|
187 |
+
2023-06-23 23:28:54 - SimpleLog - INFO: - Interactor 0 finished episode 117 with reward -1076.557 in 200 steps
|
188 |
+
2023-06-23 23:28:54 - SimpleLog - INFO: - Interactor 0 finished episode 118 with reward -1111.258 in 200 steps
|
189 |
+
2023-06-23 23:28:54 - SimpleLog - INFO: - Interactor 1 finished episode 119 with reward -761.443 in 200 steps
|
190 |
+
2023-06-23 23:28:54 - SimpleLog - INFO: - Interactor 1 finished episode 120 with reward -1165.838 in 200 steps
|
191 |
+
2023-06-23 23:28:54 - SimpleLog - INFO: - Interactor 0 finished episode 121 with reward -1002.057 in 200 steps
|
192 |
+
2023-06-23 23:28:54 - SimpleLog - INFO: - Interactor 1 finished episode 122 with reward -1099.023 in 200 steps
|
193 |
+
2023-06-23 23:28:54 - SimpleLog - INFO: - Interactor 0 finished episode 123 with reward -883.440 in 200 steps
|
194 |
+
2023-06-23 23:28:55 - SimpleLog - INFO: - Interactor 1 finished episode 124 with reward -1046.694 in 200 steps
|
195 |
+
2023-06-23 23:28:55 - SimpleLog - INFO: - Interactor 0 finished episode 125 with reward -999.911 in 200 steps
|
196 |
+
2023-06-23 23:28:55 - SimpleLog - INFO: - Interactor 0 finished episode 126 with reward -893.227 in 200 steps
|
197 |
+
2023-06-23 23:28:55 - SimpleLog - INFO: - Interactor 1 finished episode 127 with reward -1109.468 in 200 steps
|
198 |
+
2023-06-23 23:28:55 - SimpleLog - INFO: - Interactor 1 finished episode 128 with reward -998.405 in 200 steps
|
199 |
+
2023-06-23 23:28:56 - SimpleLog - INFO: - update_step: 100, online_eval_reward: -858.747
|
200 |
+
2023-06-23 23:28:56 - SimpleLog - INFO: - Interactor 0 finished episode 129 with reward -773.563 in 200 steps
|
201 |
+
2023-06-23 23:28:56 - SimpleLog - INFO: - Interactor 1 finished episode 130 with reward -889.077 in 200 steps
|
202 |
+
2023-06-23 23:28:56 - SimpleLog - INFO: - Interactor 0 finished episode 131 with reward -1215.363 in 200 steps
|
203 |
+
2023-06-23 23:28:56 - SimpleLog - INFO: - Interactor 1 finished episode 132 with reward -859.453 in 200 steps
|
204 |
+
2023-06-23 23:28:56 - SimpleLog - INFO: - Interactor 0 finished episode 133 with reward -1164.861 in 200 steps
|
205 |
+
2023-06-23 23:28:56 - SimpleLog - INFO: - Interactor 1 finished episode 134 with reward -1299.941 in 200 steps
|
206 |
+
2023-06-23 23:28:57 - SimpleLog - INFO: - Interactor 0 finished episode 135 with reward -1067.755 in 200 steps
|
207 |
+
2023-06-23 23:28:57 - SimpleLog - INFO: - Interactor 0 finished episode 136 with reward -979.356 in 200 steps
|
208 |
+
2023-06-23 23:28:57 - SimpleLog - INFO: - Interactor 1 finished episode 137 with reward -1138.386 in 200 steps
|
209 |
+
2023-06-23 23:28:57 - SimpleLog - INFO: - Interactor 1 finished episode 138 with reward -998.469 in 200 steps
|
210 |
+
2023-06-23 23:28:57 - SimpleLog - INFO: - Interactor 0 finished episode 139 with reward -1049.958 in 200 steps
|
211 |
+
2023-06-23 23:28:57 - SimpleLog - INFO: - Interactor 1 finished episode 140 with reward -1173.436 in 200 steps
|
212 |
+
2023-06-23 23:28:58 - SimpleLog - INFO: - update_step: 110, online_eval_reward: -987.739
|
213 |
+
2023-06-23 23:28:58 - SimpleLog - INFO: - Interactor 0 finished episode 141 with reward -1124.496 in 200 steps
|
214 |
+
2023-06-23 23:28:58 - SimpleLog - INFO: - Interactor 1 finished episode 142 with reward -1029.492 in 200 steps
|
215 |
+
2023-06-23 23:28:58 - SimpleLog - INFO: - Interactor 0 finished episode 143 with reward -993.167 in 200 steps
|
216 |
+
2023-06-23 23:28:58 - SimpleLog - INFO: - Interactor 1 finished episode 144 with reward -1143.786 in 200 steps
|
217 |
+
2023-06-23 23:28:59 - SimpleLog - INFO: - Interactor 0 finished episode 145 with reward -1042.199 in 200 steps
|
218 |
+
2023-06-23 23:28:59 - SimpleLog - INFO: - Interactor 0 finished episode 146 with reward -871.841 in 200 steps
|
219 |
+
2023-06-23 23:28:59 - SimpleLog - INFO: - Interactor 1 finished episode 147 with reward -1133.217 in 200 steps
|
220 |
+
2023-06-23 23:28:59 - SimpleLog - INFO: - Interactor 1 finished episode 148 with reward -884.485 in 200 steps
|
221 |
+
2023-06-23 23:28:59 - SimpleLog - INFO: - Interactor 0 finished episode 149 with reward -768.664 in 200 steps
|
222 |
+
2023-06-23 23:28:59 - SimpleLog - INFO: - Interactor 1 finished episode 150 with reward -843.489 in 200 steps
|
223 |
+
2023-06-23 23:28:59 - SimpleLog - INFO: - Interactor 0 finished episode 151 with reward -932.860 in 200 steps
|
224 |
+
2023-06-23 23:29:00 - SimpleLog - INFO: - Interactor 1 finished episode 152 with reward -879.677 in 200 steps
|
225 |
+
2023-06-23 23:29:00 - SimpleLog - INFO: - update_step: 120, online_eval_reward: -1238.290
|
226 |
+
2023-06-23 23:29:00 - SimpleLog - INFO: - Interactor 0 finished episode 153 with reward -902.371 in 200 steps
|
227 |
+
2023-06-23 23:29:00 - SimpleLog - INFO: - Interactor 0 finished episode 154 with reward -1386.070 in 200 steps
|
228 |
+
2023-06-23 23:29:00 - SimpleLog - INFO: - Interactor 1 finished episode 155 with reward -941.022 in 200 steps
|
229 |
+
2023-06-23 23:29:00 - SimpleLog - INFO: - Interactor 1 finished episode 156 with reward -1333.177 in 200 steps
|
230 |
+
2023-06-23 23:29:01 - SimpleLog - INFO: - Interactor 0 finished episode 157 with reward -1133.063 in 200 steps
|
231 |
+
2023-06-23 23:29:01 - SimpleLog - INFO: - Interactor 1 finished episode 158 with reward -1243.536 in 200 steps
|
232 |
+
2023-06-23 23:29:01 - SimpleLog - INFO: - Interactor 0 finished episode 159 with reward -1132.809 in 200 steps
|
233 |
+
2023-06-23 23:29:01 - SimpleLog - INFO: - Interactor 1 finished episode 160 with reward -1183.210 in 200 steps
|
234 |
+
2023-06-23 23:29:01 - SimpleLog - INFO: - Interactor 0 finished episode 161 with reward -1079.101 in 200 steps
|
235 |
+
2023-06-23 23:29:01 - SimpleLog - INFO: - Interactor 1 finished episode 162 with reward -1213.020 in 200 steps
|
236 |
+
2023-06-23 23:29:02 - SimpleLog - INFO: - Interactor 0 finished episode 163 with reward -998.535 in 200 steps
|
237 |
+
2023-06-23 23:29:02 - SimpleLog - INFO: - Interactor 0 finished episode 164 with reward -651.557 in 200 steps
|
238 |
+
2023-06-23 23:29:02 - SimpleLog - INFO: - Interactor 1 finished episode 165 with reward -1130.209 in 200 steps
|
239 |
+
2023-06-23 23:29:02 - SimpleLog - INFO: - Interactor 1 finished episode 166 with reward -863.091 in 200 steps
|
240 |
+
2023-06-23 23:29:02 - SimpleLog - INFO: - update_step: 130, online_eval_reward: -868.606
|
241 |
+
2023-06-23 23:29:03 - SimpleLog - INFO: - Interactor 0 finished episode 167 with reward -734.325 in 200 steps
|
242 |
+
2023-06-23 23:29:03 - SimpleLog - INFO: - Interactor 1 finished episode 168 with reward -882.276 in 200 steps
|
243 |
+
2023-06-23 23:29:03 - SimpleLog - INFO: - Interactor 0 finished episode 169 with reward -876.196 in 200 steps
|
244 |
+
2023-06-23 23:29:03 - SimpleLog - INFO: - Interactor 1 finished episode 170 with reward -876.921 in 200 steps
|
245 |
+
2023-06-23 23:29:03 - SimpleLog - INFO: - Interactor 0 finished episode 171 with reward -898.159 in 200 steps
|
246 |
+
2023-06-23 23:29:03 - SimpleLog - INFO: - Interactor 0 finished episode 172 with reward -766.936 in 200 steps
|
247 |
+
2023-06-23 23:29:03 - SimpleLog - INFO: - Interactor 1 finished episode 173 with reward -1003.818 in 200 steps
|
248 |
+
2023-06-23 23:29:03 - SimpleLog - INFO: - Interactor 1 finished episode 174 with reward -912.371 in 200 steps
|
249 |
+
2023-06-23 23:29:04 - SimpleLog - INFO: - Interactor 0 finished episode 175 with reward -820.263 in 200 steps
|
250 |
+
2023-06-23 23:29:04 - SimpleLog - INFO: - Interactor 1 finished episode 176 with reward -886.168 in 200 steps
|
251 |
+
2023-06-23 23:29:04 - SimpleLog - INFO: - Interactor 0 finished episode 177 with reward -1011.260 in 200 steps
|
252 |
+
2023-06-23 23:29:04 - SimpleLog - INFO: - Interactor 1 finished episode 178 with reward -1041.768 in 200 steps
|
253 |
+
2023-06-23 23:29:05 - SimpleLog - INFO: - update_step: 140, online_eval_reward: -967.978
|
254 |
+
2023-06-23 23:29:05 - SimpleLog - INFO: - Interactor 0 finished episode 179 with reward -930.469 in 200 steps
|
255 |
+
2023-06-23 23:29:05 - SimpleLog - INFO: - Interactor 1 finished episode 180 with reward -1166.417 in 200 steps
|
256 |
+
2023-06-23 23:29:05 - SimpleLog - INFO: - Interactor 0 finished episode 181 with reward -899.961 in 200 steps
|
257 |
+
2023-06-23 23:29:05 - SimpleLog - INFO: - Interactor 0 finished episode 182 with reward -948.550 in 200 steps
|
258 |
+
2023-06-23 23:29:05 - SimpleLog - INFO: - Interactor 1 finished episode 183 with reward -1049.494 in 200 steps
|
259 |
+
2023-06-23 23:29:05 - SimpleLog - INFO: - Interactor 1 finished episode 184 with reward -1012.236 in 200 steps
|
260 |
+
2023-06-23 23:29:06 - SimpleLog - INFO: - Interactor 0 finished episode 185 with reward -884.435 in 200 steps
|
261 |
+
2023-06-23 23:29:06 - SimpleLog - INFO: - Interactor 1 finished episode 186 with reward -1099.587 in 200 steps
|
262 |
+
2023-06-23 23:29:06 - SimpleLog - INFO: - Interactor 0 finished episode 187 with reward -772.576 in 200 steps
|
263 |
+
2023-06-23 23:29:06 - SimpleLog - INFO: - Interactor 1 finished episode 188 with reward -1018.542 in 200 steps
|
264 |
+
2023-06-23 23:29:06 - SimpleLog - INFO: - Interactor 0 finished episode 189 with reward -774.274 in 200 steps
|
265 |
+
2023-06-23 23:29:06 - SimpleLog - INFO: - Interactor 0 finished episode 190 with reward -1219.552 in 200 steps
|
266 |
+
2023-06-23 23:29:06 - SimpleLog - INFO: - Interactor 1 finished episode 191 with reward -1003.790 in 200 steps
|
267 |
+
2023-06-23 23:29:07 - SimpleLog - INFO: - Interactor 1 finished episode 192 with reward -767.358 in 200 steps
|
268 |
+
2023-06-23 23:29:07 - SimpleLog - INFO: - update_step: 150, online_eval_reward: -899.874
|
269 |
+
2023-06-23 23:29:07 - SimpleLog - INFO: - Interactor 0 finished episode 193 with reward -848.654 in 200 steps
|
270 |
+
2023-06-23 23:29:07 - SimpleLog - INFO: - Interactor 1 finished episode 194 with reward -949.951 in 200 steps
|
271 |
+
2023-06-23 23:29:08 - SimpleLog - INFO: - Interactor 0 finished episode 195 with reward -808.256 in 200 steps
|
272 |
+
2023-06-23 23:29:08 - SimpleLog - INFO: - Interactor 1 finished episode 196 with reward -1024.067 in 200 steps
|
273 |
+
2023-06-23 23:29:08 - SimpleLog - INFO: - Interactor 0 finished episode 197 with reward -892.825 in 200 steps
|
274 |
+
2023-06-23 23:29:08 - SimpleLog - INFO: - Interactor 1 finished episode 198 with reward -1016.267 in 200 steps
|
275 |
+
2023-06-23 23:29:08 - SimpleLog - INFO: - Interactor 0 finished episode 199 with reward -896.411 in 200 steps
|
276 |
+
2023-06-23 23:29:08 - SimpleLog - INFO: - Interactor 0 finished episode 200 with reward -657.542 in 200 steps
|
277 |
+
2023-06-23 23:29:08 - SimpleLog - INFO: - Interactor 1 finished episode 201 with reward -999.630 in 200 steps
|
278 |
+
2023-06-23 23:29:08 - SimpleLog - INFO: - Interactor 1 finished episode 202 with reward -860.776 in 200 steps
|
279 |
+
2023-06-23 23:29:09 - SimpleLog - INFO: - Interactor 0 finished episode 203 with reward -774.604 in 200 steps
|
280 |
+
2023-06-23 23:29:09 - SimpleLog - INFO: - Interactor 1 finished episode 204 with reward -879.799 in 200 steps
|
281 |
+
2023-06-23 23:29:09 - SimpleLog - INFO: - update_step: 160, online_eval_reward: -1165.182
|
282 |
+
2023-06-23 23:29:10 - SimpleLog - INFO: - Interactor 0 finished episode 205 with reward -762.809 in 200 steps
|
283 |
+
2023-06-23 23:29:10 - SimpleLog - INFO: - Interactor 1 finished episode 206 with reward -1065.543 in 200 steps
|
284 |
+
2023-06-23 23:29:10 - SimpleLog - INFO: - Interactor 0 finished episode 207 with reward -1207.320 in 200 steps
|
285 |
+
2023-06-23 23:29:10 - SimpleLog - INFO: - Interactor 1 finished episode 208 with reward -1207.391 in 200 steps
|
286 |
+
2023-06-23 23:29:10 - SimpleLog - INFO: - Interactor 0 finished episode 209 with reward -1424.258 in 200 steps
|
287 |
+
2023-06-23 23:29:10 - SimpleLog - INFO: - Interactor 0 finished episode 210 with reward -1328.323 in 200 steps
|
288 |
+
2023-06-23 23:29:10 - SimpleLog - INFO: - Interactor 1 finished episode 211 with reward -1490.923 in 200 steps
|
289 |
+
2023-06-23 23:29:10 - SimpleLog - INFO: - Interactor 1 finished episode 212 with reward -1286.429 in 200 steps
|
290 |
+
2023-06-23 23:29:11 - SimpleLog - INFO: - Interactor 0 finished episode 213 with reward -1223.944 in 200 steps
|
291 |
+
2023-06-23 23:29:11 - SimpleLog - INFO: - Interactor 1 finished episode 214 with reward -765.624 in 200 steps
|
292 |
+
2023-06-23 23:29:11 - SimpleLog - INFO: - Interactor 0 finished episode 215 with reward -929.011 in 200 steps
|
293 |
+
2023-06-23 23:29:11 - SimpleLog - INFO: - Interactor 1 finished episode 216 with reward -769.381 in 200 steps
|
294 |
+
2023-06-23 23:29:12 - SimpleLog - INFO: - update_step: 170, online_eval_reward: -871.098
|
295 |
+
2023-06-23 23:29:12 - SimpleLog - INFO: - Interactor 0 finished episode 217 with reward -644.503 in 200 steps
|
296 |
+
2023-06-23 23:29:12 - SimpleLog - INFO: - Interactor 0 finished episode 218 with reward -768.482 in 200 steps
|
297 |
+
2023-06-23 23:29:12 - SimpleLog - INFO: - Interactor 1 finished episode 219 with reward -888.498 in 200 steps
|
298 |
+
2023-06-23 23:29:12 - SimpleLog - INFO: - Interactor 1 finished episode 220 with reward -1049.285 in 200 steps
|
299 |
+
2023-06-23 23:29:12 - SimpleLog - INFO: - Interactor 0 finished episode 221 with reward -442.022 in 200 steps
|
300 |
+
2023-06-23 23:29:12 - SimpleLog - INFO: - Interactor 1 finished episode 222 with reward -682.073 in 200 steps
|
301 |
+
2023-06-23 23:29:13 - SimpleLog - INFO: - Interactor 0 finished episode 223 with reward -672.204 in 200 steps
|
302 |
+
2023-06-23 23:29:13 - SimpleLog - INFO: - Interactor 1 finished episode 224 with reward -887.488 in 200 steps
|
303 |
+
2023-06-23 23:29:13 - SimpleLog - INFO: - Interactor 0 finished episode 225 with reward -1117.814 in 200 steps
|
304 |
+
2023-06-23 23:29:13 - SimpleLog - INFO: - Interactor 1 finished episode 226 with reward -935.699 in 200 steps
|
305 |
+
2023-06-23 23:29:13 - SimpleLog - INFO: - Interactor 0 finished episode 227 with reward -1056.983 in 200 steps
|
306 |
+
2023-06-23 23:29:13 - SimpleLog - INFO: - Interactor 0 finished episode 228 with reward -774.419 in 200 steps
|
307 |
+
2023-06-23 23:29:13 - SimpleLog - INFO: - Interactor 1 finished episode 229 with reward -784.042 in 200 steps
|
308 |
+
2023-06-23 23:29:13 - SimpleLog - INFO: - Interactor 1 finished episode 230 with reward -1027.609 in 200 steps
|
309 |
+
2023-06-23 23:29:14 - SimpleLog - INFO: - update_step: 180, online_eval_reward: -1022.731
|
310 |
+
2023-06-23 23:29:14 - SimpleLog - INFO: - Interactor 0 finished episode 231 with reward -968.033 in 200 steps
|
311 |
+
2023-06-23 23:29:14 - SimpleLog - INFO: - Interactor 1 finished episode 232 with reward -1097.376 in 200 steps
|
312 |
+
2023-06-23 23:29:15 - SimpleLog - INFO: - Interactor 0 finished episode 233 with reward -898.466 in 200 steps
|
313 |
+
2023-06-23 23:29:15 - SimpleLog - INFO: - Interactor 1 finished episode 234 with reward -1153.315 in 200 steps
|
314 |
+
2023-06-23 23:29:15 - SimpleLog - INFO: - Interactor 0 finished episode 235 with reward -786.587 in 200 steps
|
315 |
+
2023-06-23 23:29:15 - SimpleLog - INFO: - Interactor 0 finished episode 236 with reward -793.713 in 200 steps
|
316 |
+
2023-06-23 23:29:15 - SimpleLog - INFO: - Interactor 1 finished episode 237 with reward -837.508 in 200 steps
|
317 |
+
2023-06-23 23:29:15 - SimpleLog - INFO: - Interactor 1 finished episode 238 with reward -900.971 in 200 steps
|
318 |
+
2023-06-23 23:29:15 - SimpleLog - INFO: - Interactor 0 finished episode 239 with reward -891.381 in 200 steps
|
319 |
+
2023-06-23 23:29:15 - SimpleLog - INFO: - Interactor 1 finished episode 240 with reward -913.762 in 200 steps
|
320 |
+
2023-06-23 23:29:16 - SimpleLog - INFO: - Interactor 0 finished episode 241 with reward -806.666 in 200 steps
|
321 |
+
2023-06-23 23:29:16 - SimpleLog - INFO: - Interactor 1 finished episode 242 with reward -1005.761 in 200 steps
|
322 |
+
2023-06-23 23:29:16 - SimpleLog - INFO: - update_step: 190, online_eval_reward: -902.825
|
323 |
+
2023-06-23 23:29:16 - SimpleLog - INFO: - Interactor 0 finished episode 243 with reward -774.207 in 200 steps
|
324 |
+
2023-06-23 23:29:17 - SimpleLog - INFO: - Interactor 1 finished episode 244 with reward -764.939 in 200 steps
|
325 |
+
2023-06-23 23:29:17 - SimpleLog - INFO: - Interactor 0 finished episode 245 with reward -783.787 in 200 steps
|
326 |
+
2023-06-23 23:29:17 - SimpleLog - INFO: - Interactor 0 finished episode 246 with reward -762.004 in 200 steps
|
327 |
+
2023-06-23 23:29:17 - SimpleLog - INFO: - Interactor 1 finished episode 247 with reward -1004.212 in 200 steps
|
328 |
+
2023-06-23 23:29:17 - SimpleLog - INFO: - Interactor 1 finished episode 248 with reward -1048.482 in 200 steps
|
329 |
+
2023-06-23 23:29:17 - SimpleLog - INFO: - Interactor 0 finished episode 249 with reward -939.305 in 200 steps
|
330 |
+
2023-06-23 23:29:17 - SimpleLog - INFO: - Interactor 1 finished episode 250 with reward -1187.124 in 200 steps
|
331 |
+
2023-06-23 23:29:18 - SimpleLog - INFO: - Interactor 0 finished episode 251 with reward -1055.580 in 200 steps
|
332 |
+
2023-06-23 23:29:18 - SimpleLog - INFO: - Interactor 1 finished episode 252 with reward -1196.236 in 200 steps
|
333 |
+
2023-06-23 23:29:18 - SimpleLog - INFO: - Interactor 0 finished episode 253 with reward -1046.953 in 200 steps
|
334 |
+
2023-06-23 23:29:18 - SimpleLog - INFO: - Interactor 0 finished episode 254 with reward -717.520 in 200 steps
|
335 |
+
2023-06-23 23:29:18 - SimpleLog - INFO: - Interactor 1 finished episode 255 with reward -1154.200 in 200 steps
|
336 |
+
2023-06-23 23:29:18 - SimpleLog - INFO: - Interactor 1 finished episode 256 with reward -889.865 in 200 steps
|
337 |
+
2023-06-23 23:29:19 - SimpleLog - INFO: - update_step: 200, online_eval_reward: -945.271
|
338 |
+
2023-06-23 23:29:19 - SimpleLog - INFO: - Interactor 0 finished episode 257 with reward -823.443 in 200 steps
|
339 |
+
2023-06-23 23:29:19 - SimpleLog - INFO: - Interactor 1 finished episode 258 with reward -902.464 in 200 steps
|
340 |
+
2023-06-23 23:29:19 - SimpleLog - INFO: - Interactor 0 finished episode 259 with reward -886.510 in 200 steps
|
341 |
+
2023-06-23 23:29:19 - SimpleLog - INFO: - Interactor 1 finished episode 260 with reward -1033.214 in 200 steps
|
342 |
+
2023-06-23 23:29:19 - SimpleLog - INFO: - Interactor 0 finished episode 261 with reward -773.826 in 200 steps
|
343 |
+
2023-06-23 23:29:20 - SimpleLog - INFO: - Interactor 1 finished episode 262 with reward -772.516 in 200 steps
|
344 |
+
2023-06-23 23:29:20 - SimpleLog - INFO: - Interactor 0 finished episode 263 with reward -625.720 in 200 steps
|
345 |
+
2023-06-23 23:29:20 - SimpleLog - INFO: - Interactor 0 finished episode 264 with reward -532.556 in 200 steps
|
346 |
+
2023-06-23 23:29:20 - SimpleLog - INFO: - Interactor 1 finished episode 265 with reward -905.783 in 200 steps
|
347 |
+
2023-06-23 23:29:20 - SimpleLog - INFO: - Interactor 1 finished episode 266 with reward -711.658 in 200 steps
|
348 |
+
2023-06-23 23:29:20 - SimpleLog - INFO: - Interactor 0 finished episode 267 with reward -697.670 in 200 steps
|
349 |
+
2023-06-23 23:29:20 - SimpleLog - INFO: - Interactor 1 finished episode 268 with reward -737.132 in 200 steps
|
350 |
+
2023-06-23 23:29:21 - SimpleLog - INFO: - update_step: 210, online_eval_reward: -637.398
|
351 |
+
2023-06-23 23:29:21 - SimpleLog - INFO: - Interactor 0 finished episode 269 with reward -518.297 in 200 steps
|
352 |
+
2023-06-23 23:29:21 - SimpleLog - INFO: - Interactor 1 finished episode 270 with reward -766.025 in 200 steps
|
353 |
+
2023-06-23 23:29:21 - SimpleLog - INFO: - Interactor 0 finished episode 271 with reward -516.168 in 200 steps
|
354 |
+
2023-06-23 23:29:22 - SimpleLog - INFO: - Interactor 1 finished episode 272 with reward -825.876 in 200 steps
|
355 |
+
2023-06-23 23:29:22 - SimpleLog - INFO: - Interactor 0 finished episode 273 with reward -611.496 in 200 steps
|
356 |
+
2023-06-23 23:29:22 - SimpleLog - INFO: - Interactor 0 finished episode 274 with reward -760.451 in 200 steps
|
357 |
+
2023-06-23 23:29:22 - SimpleLog - INFO: - Interactor 1 finished episode 275 with reward -790.245 in 200 steps
|
358 |
+
2023-06-23 23:29:22 - SimpleLog - INFO: - Interactor 1 finished episode 276 with reward -991.816 in 200 steps
|
359 |
+
2023-06-23 23:29:22 - SimpleLog - INFO: - Interactor 0 finished episode 277 with reward -770.478 in 200 steps
|
360 |
+
2023-06-23 23:29:22 - SimpleLog - INFO: - Interactor 1 finished episode 278 with reward -1015.628 in 200 steps
|
361 |
+
2023-06-23 23:29:23 - SimpleLog - INFO: - Interactor 0 finished episode 279 with reward -772.373 in 200 steps
|
362 |
+
2023-06-23 23:29:23 - SimpleLog - INFO: - Interactor 1 finished episode 280 with reward -1034.516 in 200 steps
|
363 |
+
2023-06-23 23:29:23 - SimpleLog - INFO: - update_step: 220, online_eval_reward: -896.776
|
364 |
+
2023-06-23 23:29:23 - SimpleLog - INFO: - Interactor 0 finished episode 281 with reward -1011.119 in 200 steps
|
365 |
+
2023-06-23 23:29:23 - SimpleLog - INFO: - Interactor 0 finished episode 282 with reward -905.922 in 200 steps
|
366 |
+
2023-06-23 23:29:23 - SimpleLog - INFO: - Interactor 1 finished episode 283 with reward -1035.188 in 200 steps
|
367 |
+
2023-06-23 23:29:24 - SimpleLog - INFO: - Interactor 1 finished episode 284 with reward -1036.556 in 200 steps
|
368 |
+
2023-06-23 23:29:24 - SimpleLog - INFO: - Interactor 0 finished episode 285 with reward -646.115 in 200 steps
|
369 |
+
2023-06-23 23:29:24 - SimpleLog - INFO: - Interactor 1 finished episode 286 with reward -1053.022 in 200 steps
|
370 |
+
2023-06-23 23:29:24 - SimpleLog - INFO: - Interactor 0 finished episode 287 with reward -766.578 in 200 steps
|
371 |
+
2023-06-23 23:29:24 - SimpleLog - INFO: - Interactor 1 finished episode 288 with reward -1028.109 in 200 steps
|
372 |
+
2023-06-23 23:29:25 - SimpleLog - INFO: - Interactor 0 finished episode 289 with reward -572.439 in 200 steps
|
373 |
+
2023-06-23 23:29:25 - SimpleLog - INFO: - Interactor 1 finished episode 290 with reward -900.955 in 200 steps
|
374 |
+
2023-06-23 23:29:25 - SimpleLog - INFO: - Interactor 0 finished episode 291 with reward -586.545 in 200 steps
|
375 |
+
2023-06-23 23:29:25 - SimpleLog - INFO: - Interactor 0 finished episode 292 with reward -813.407 in 200 steps
|
376 |
+
2023-06-23 23:29:25 - SimpleLog - INFO: - Interactor 1 finished episode 293 with reward -1033.745 in 200 steps
|
377 |
+
2023-06-23 23:29:25 - SimpleLog - INFO: - Interactor 1 finished episode 294 with reward -774.579 in 200 steps
|
378 |
+
2023-06-23 23:29:26 - SimpleLog - INFO: - update_step: 230, online_eval_reward: -966.754
|
379 |
+
2023-06-23 23:29:26 - SimpleLog - INFO: - Interactor 0 finished episode 295 with reward -843.954 in 200 steps
|
380 |
+
2023-06-23 23:29:26 - SimpleLog - INFO: - Interactor 1 finished episode 296 with reward -1008.721 in 200 steps
|
381 |
+
2023-06-23 23:29:26 - SimpleLog - INFO: - Interactor 0 finished episode 297 with reward -388.681 in 200 steps
|
382 |
+
2023-06-23 23:29:26 - SimpleLog - INFO: - Interactor 1 finished episode 298 with reward -1057.956 in 200 steps
|
383 |
+
2023-06-23 23:29:26 - SimpleLog - INFO: - Interactor 0 finished episode 299 with reward -859.229 in 200 steps
|
384 |
+
2023-06-23 23:29:27 - SimpleLog - INFO: - Interactor 0 finished episode 300 with reward -657.231 in 200 steps
|
385 |
+
2023-06-23 23:29:27 - SimpleLog - INFO: - Interactor 1 finished episode 301 with reward -1046.838 in 200 steps
|
386 |
+
2023-06-23 23:29:27 - SimpleLog - INFO: - Interactor 1 finished episode 302 with reward -1051.318 in 200 steps
|
387 |
+
2023-06-23 23:29:27 - SimpleLog - INFO: - Interactor 0 finished episode 303 with reward -656.655 in 200 steps
|
388 |
+
2023-06-23 23:29:27 - SimpleLog - INFO: - Interactor 1 finished episode 304 with reward -1070.768 in 200 steps
|
389 |
+
2023-06-23 23:29:27 - SimpleLog - INFO: - Interactor 0 finished episode 305 with reward -903.185 in 200 steps
|
390 |
+
2023-06-23 23:29:27 - SimpleLog - INFO: - Interactor 1 finished episode 306 with reward -1125.895 in 200 steps
|
391 |
+
2023-06-23 23:29:28 - SimpleLog - INFO: - update_step: 240, online_eval_reward: -949.363
|
392 |
+
2023-06-23 23:29:28 - SimpleLog - INFO: - Interactor 0 finished episode 307 with reward -648.462 in 200 steps
|
393 |
+
2023-06-23 23:29:28 - SimpleLog - INFO: - Interactor 1 finished episode 308 with reward -1026.517 in 200 steps
|
394 |
+
2023-06-23 23:29:28 - SimpleLog - INFO: - Interactor 0 finished episode 309 with reward -928.862 in 200 steps
|
395 |
+
2023-06-23 23:29:28 - SimpleLog - INFO: - Interactor 0 finished episode 310 with reward -1082.339 in 200 steps
|
396 |
+
2023-06-23 23:29:29 - SimpleLog - INFO: - Interactor 1 finished episode 311 with reward -1092.708 in 200 steps
|
397 |
+
2023-06-23 23:29:29 - SimpleLog - INFO: - Interactor 1 finished episode 312 with reward -933.012 in 200 steps
|
398 |
+
2023-06-23 23:29:29 - SimpleLog - INFO: - Interactor 0 finished episode 313 with reward -946.489 in 200 steps
|
399 |
+
2023-06-23 23:29:29 - SimpleLog - INFO: - Interactor 1 finished episode 314 with reward -1155.686 in 200 steps
|
400 |
+
2023-06-23 23:29:29 - SimpleLog - INFO: - Interactor 0 finished episode 315 with reward -1055.120 in 200 steps
|
401 |
+
2023-06-23 23:29:29 - SimpleLog - INFO: - Interactor 1 finished episode 316 with reward -1210.636 in 200 steps
|
402 |
+
2023-06-23 23:29:30 - SimpleLog - INFO: - Interactor 0 finished episode 317 with reward -947.896 in 200 steps
|
403 |
+
2023-06-23 23:29:30 - SimpleLog - INFO: - Interactor 0 finished episode 318 with reward -752.115 in 200 steps
|
404 |
+
2023-06-23 23:29:30 - SimpleLog - INFO: - Interactor 1 finished episode 319 with reward -1060.215 in 200 steps
|
405 |
+
2023-06-23 23:29:30 - SimpleLog - INFO: - Interactor 1 finished episode 320 with reward -910.203 in 200 steps
|
406 |
+
2023-06-23 23:29:30 - SimpleLog - INFO: - update_step: 250, online_eval_reward: -751.431
|
407 |
+
2023-06-23 23:29:30 - SimpleLog - INFO: - Interactor 0 finished episode 321 with reward -521.808 in 200 steps
|
408 |
+
2023-06-23 23:29:31 - SimpleLog - INFO: - Interactor 1 finished episode 322 with reward -903.211 in 200 steps
|
409 |
+
2023-06-23 23:29:31 - SimpleLog - INFO: - Interactor 0 finished episode 323 with reward -657.212 in 200 steps
|
410 |
+
2023-06-23 23:29:31 - SimpleLog - INFO: - Interactor 1 finished episode 324 with reward -1036.603 in 200 steps
|
411 |
+
2023-06-23 23:29:31 - SimpleLog - INFO: - Interactor 0 finished episode 325 with reward -669.511 in 200 steps
|
412 |
+
2023-06-23 23:29:31 - SimpleLog - INFO: - Interactor 1 finished episode 326 with reward -648.863 in 200 steps
|
413 |
+
2023-06-23 23:29:32 - SimpleLog - INFO: - Interactor 0 finished episode 327 with reward -522.373 in 200 steps
|
414 |
+
2023-06-23 23:29:32 - SimpleLog - INFO: - Interactor 0 finished episode 328 with reward -896.716 in 200 steps
|
415 |
+
2023-06-23 23:29:32 - SimpleLog - INFO: - Interactor 1 finished episode 329 with reward -715.516 in 200 steps
|
416 |
+
2023-06-23 23:29:32 - SimpleLog - INFO: - Interactor 1 finished episode 330 with reward -775.273 in 200 steps
|
417 |
+
2023-06-23 23:29:32 - SimpleLog - INFO: - Interactor 0 finished episode 331 with reward -775.760 in 200 steps
|
418 |
+
2023-06-23 23:29:32 - SimpleLog - INFO: - Interactor 1 finished episode 332 with reward -901.585 in 200 steps
|
419 |
+
2023-06-23 23:29:33 - SimpleLog - INFO: - update_step: 260, online_eval_reward: -882.195
|
420 |
+
2023-06-23 23:29:33 - SimpleLog - INFO: - Interactor 0 finished episode 333 with reward -798.452 in 200 steps
|
421 |
+
2023-06-23 23:29:33 - SimpleLog - INFO: - Interactor 1 finished episode 334 with reward -655.894 in 200 steps
|
422 |
+
2023-06-23 23:29:33 - SimpleLog - INFO: - Interactor 0 finished episode 335 with reward -652.146 in 200 steps
|
423 |
+
2023-06-23 23:29:33 - SimpleLog - INFO: - Interactor 1 finished episode 336 with reward -1008.630 in 200 steps
|
424 |
+
2023-06-23 23:29:34 - SimpleLog - INFO: - Interactor 0 finished episode 337 with reward -675.097 in 200 steps
|
425 |
+
2023-06-23 23:29:34 - SimpleLog - INFO: - Interactor 0 finished episode 338 with reward -935.394 in 200 steps
|
426 |
+
2023-06-23 23:29:34 - SimpleLog - INFO: - Interactor 1 finished episode 339 with reward -1036.289 in 200 steps
|
427 |
+
2023-06-23 23:29:34 - SimpleLog - INFO: - Interactor 1 finished episode 340 with reward -842.345 in 200 steps
|
428 |
+
2023-06-23 23:29:34 - SimpleLog - INFO: - Interactor 0 finished episode 341 with reward -1245.671 in 200 steps
|
429 |
+
2023-06-23 23:29:34 - SimpleLog - INFO: - Interactor 1 finished episode 342 with reward -952.360 in 200 steps
|
430 |
+
2023-06-23 23:29:34 - SimpleLog - INFO: - Interactor 0 finished episode 343 with reward -1135.844 in 200 steps
|
431 |
+
2023-06-23 23:29:34 - SimpleLog - INFO: - Interactor 1 finished episode 344 with reward -953.178 in 200 steps
|
432 |
+
2023-06-23 23:29:35 - SimpleLog - INFO: - update_step: 270, online_eval_reward: -937.541
|
433 |
+
2023-06-23 23:29:35 - SimpleLog - INFO: - Interactor 0 finished episode 345 with reward -993.506 in 200 steps
|
434 |
+
2023-06-23 23:29:35 - SimpleLog - INFO: - Interactor 0 finished episode 346 with reward -542.680 in 200 steps
|
435 |
+
2023-06-23 23:29:35 - SimpleLog - INFO: - Interactor 1 finished episode 347 with reward -1000.620 in 200 steps
|
436 |
+
2023-06-23 23:29:35 - SimpleLog - INFO: - Interactor 1 finished episode 348 with reward -902.387 in 200 steps
|
437 |
+
2023-06-23 23:29:36 - SimpleLog - INFO: - Interactor 0 finished episode 349 with reward -654.987 in 200 steps
|
438 |
+
2023-06-23 23:29:36 - SimpleLog - INFO: - Interactor 1 finished episode 350 with reward -905.870 in 200 steps
|
439 |
+
2023-06-23 23:29:36 - SimpleLog - INFO: - Interactor 0 finished episode 351 with reward -747.354 in 200 steps
|
440 |
+
2023-06-23 23:29:36 - SimpleLog - INFO: - Interactor 1 finished episode 352 with reward -773.965 in 200 steps
|
441 |
+
2023-06-23 23:29:36 - SimpleLog - INFO: - Interactor 0 finished episode 353 with reward -517.016 in 200 steps
|
442 |
+
2023-06-23 23:29:36 - SimpleLog - INFO: - Interactor 1 finished episode 354 with reward -779.684 in 200 steps
|
443 |
+
2023-06-23 23:29:37 - SimpleLog - INFO: - Interactor 0 finished episode 355 with reward -605.219 in 200 steps
|
444 |
+
2023-06-23 23:29:37 - SimpleLog - INFO: - Interactor 0 finished episode 356 with reward -789.774 in 200 steps
|
445 |
+
2023-06-23 23:29:37 - SimpleLog - INFO: - Interactor 1 finished episode 357 with reward -572.265 in 200 steps
|
446 |
+
2023-06-23 23:29:37 - SimpleLog - INFO: - Interactor 1 finished episode 358 with reward -883.808 in 200 steps
|
447 |
+
2023-06-23 23:29:37 - SimpleLog - INFO: - update_step: 280, online_eval_reward: -752.478
|
448 |
+
2023-06-23 23:29:38 - SimpleLog - INFO: - Interactor 0 finished episode 359 with reward -836.779 in 200 steps
|
449 |
+
2023-06-23 23:29:38 - SimpleLog - INFO: - Interactor 1 finished episode 360 with reward -789.929 in 200 steps
|
450 |
+
2023-06-23 23:29:38 - SimpleLog - INFO: - Interactor 0 finished episode 361 with reward -905.797 in 200 steps
|
451 |
+
2023-06-23 23:29:38 - SimpleLog - INFO: - Interactor 1 finished episode 362 with reward -846.928 in 200 steps
|
452 |
+
2023-06-23 23:29:38 - SimpleLog - INFO: - Interactor 0 finished episode 363 with reward -957.115 in 200 steps
|
453 |
+
2023-06-23 23:29:38 - SimpleLog - INFO: - Interactor 0 finished episode 364 with reward -755.656 in 200 steps
|
454 |
+
2023-06-23 23:29:38 - SimpleLog - INFO: - Interactor 1 finished episode 365 with reward -555.637 in 200 steps
|
455 |
+
2023-06-23 23:29:38 - SimpleLog - INFO: - Interactor 1 finished episode 366 with reward -646.260 in 200 steps
|
456 |
+
2023-06-23 23:29:39 - SimpleLog - INFO: - Interactor 0 finished episode 367 with reward -786.071 in 200 steps
|
457 |
+
2023-06-23 23:29:39 - SimpleLog - INFO: - Interactor 1 finished episode 368 with reward -906.410 in 200 steps
|
458 |
+
2023-06-23 23:29:39 - SimpleLog - INFO: - Interactor 0 finished episode 369 with reward -745.088 in 200 steps
|
459 |
+
2023-06-23 23:29:39 - SimpleLog - INFO: - Interactor 1 finished episode 370 with reward -890.389 in 200 steps
|
460 |
+
2023-06-23 23:29:40 - SimpleLog - INFO: - update_step: 290, online_eval_reward: -868.987
|
461 |
+
2023-06-23 23:29:40 - SimpleLog - INFO: - Interactor 0 finished episode 371 with reward -773.146 in 200 steps
|
462 |
+
2023-06-23 23:29:40 - SimpleLog - INFO: - Interactor 1 finished episode 372 with reward -824.539 in 200 steps
|
463 |
+
2023-06-23 23:29:40 - SimpleLog - INFO: - Interactor 0 finished episode 373 with reward -520.322 in 200 steps
|
464 |
+
2023-06-23 23:29:40 - SimpleLog - INFO: - Interactor 0 finished episode 374 with reward -389.849 in 200 steps
|
465 |
+
2023-06-23 23:29:40 - SimpleLog - INFO: - Interactor 1 finished episode 375 with reward -774.150 in 200 steps
|
466 |
+
2023-06-23 23:29:40 - SimpleLog - INFO: - Interactor 1 finished episode 376 with reward -649.526 in 200 steps
|
467 |
+
2023-06-23 23:29:41 - SimpleLog - INFO: - Interactor 0 finished episode 377 with reward -650.166 in 200 steps
|
468 |
+
2023-06-23 23:29:41 - SimpleLog - INFO: - Interactor 1 finished episode 378 with reward -699.467 in 200 steps
|
469 |
+
2023-06-23 23:29:41 - SimpleLog - INFO: - Interactor 0 finished episode 379 with reward -618.373 in 200 steps
|
470 |
+
2023-06-23 23:29:41 - SimpleLog - INFO: - Interactor 1 finished episode 380 with reward -767.637 in 200 steps
|
471 |
+
2023-06-23 23:29:41 - SimpleLog - INFO: - Interactor 0 finished episode 381 with reward -558.887 in 200 steps
|
472 |
+
2023-06-23 23:29:41 - SimpleLog - INFO: - Interactor 0 finished episode 382 with reward -540.393 in 200 steps
|
473 |
+
2023-06-23 23:29:41 - SimpleLog - INFO: - Interactor 1 finished episode 383 with reward -785.616 in 200 steps
|
474 |
+
2023-06-23 23:29:42 - SimpleLog - INFO: - Interactor 1 finished episode 384 with reward -903.092 in 200 steps
|
475 |
+
2023-06-23 23:29:42 - SimpleLog - INFO: - update_step: 300, online_eval_reward: -736.306
|
476 |
+
2023-06-23 23:29:42 - SimpleLog - INFO: - Interactor 0 finished episode 385 with reward -629.000 in 200 steps
|
477 |
+
2023-06-23 23:29:42 - SimpleLog - INFO: - Interactor 1 finished episode 386 with reward -519.198 in 200 steps
|
478 |
+
2023-06-23 23:29:43 - SimpleLog - INFO: - Interactor 0 finished episode 387 with reward -680.500 in 200 steps
|
479 |
+
2023-06-23 23:29:43 - SimpleLog - INFO: - Interactor 1 finished episode 388 with reward -523.967 in 200 steps
|
480 |
+
2023-06-23 23:29:43 - SimpleLog - INFO: - Interactor 0 finished episode 389 with reward -392.223 in 200 steps
|
481 |
+
2023-06-23 23:29:43 - SimpleLog - INFO: - Interactor 1 finished episode 390 with reward -518.808 in 200 steps
|
482 |
+
2023-06-23 23:29:43 - SimpleLog - INFO: - Interactor 0 finished episode 391 with reward -518.856 in 200 steps
|
483 |
+
2023-06-23 23:29:43 - SimpleLog - INFO: - Interactor 0 finished episode 392 with reward -647.841 in 200 steps
|
484 |
+
2023-06-23 23:29:43 - SimpleLog - INFO: - Interactor 1 finished episode 393 with reward -570.864 in 200 steps
|
485 |
+
2023-06-23 23:29:43 - SimpleLog - INFO: - Interactor 1 finished episode 394 with reward -899.587 in 200 steps
|
486 |
+
2023-06-23 23:29:44 - SimpleLog - INFO: - Interactor 0 finished episode 395 with reward -261.409 in 200 steps
|
487 |
+
2023-06-23 23:29:44 - SimpleLog - INFO: - Interactor 1 finished episode 396 with reward -516.554 in 200 steps
|
488 |
+
2023-06-23 23:29:44 - SimpleLog - INFO: - update_step: 310, online_eval_reward: -632.110
|
489 |
+
2023-06-23 23:29:44 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -632.110, save the best model!
|
490 |
+
2023-06-23 23:29:44 - SimpleLog - INFO: - Interactor 0 finished episode 397 with reward -523.559 in 200 steps
|
491 |
+
2023-06-23 23:29:45 - SimpleLog - INFO: - Interactor 1 finished episode 398 with reward -682.967 in 200 steps
|
492 |
+
2023-06-23 23:29:45 - SimpleLog - INFO: - Interactor 0 finished episode 399 with reward -443.381 in 200 steps
|
493 |
+
2023-06-23 23:29:45 - SimpleLog - INFO: - Interactor 1 finished episode 400 with reward -772.823 in 200 steps
|
494 |
+
2023-06-23 23:29:45 - SimpleLog - INFO: - Interactor 0 finished episode 401 with reward -498.193 in 200 steps
|
495 |
+
2023-06-23 23:29:45 - SimpleLog - INFO: - Interactor 0 finished episode 402 with reward -132.726 in 200 steps
|
496 |
+
2023-06-23 23:29:45 - SimpleLog - INFO: - Interactor 1 finished episode 403 with reward -266.268 in 200 steps
|
497 |
+
2023-06-23 23:29:45 - SimpleLog - INFO: - Interactor 1 finished episode 404 with reward -516.921 in 200 steps
|
498 |
+
2023-06-23 23:29:46 - SimpleLog - INFO: - Interactor 0 finished episode 405 with reward -130.883 in 200 steps
|
499 |
+
2023-06-23 23:29:46 - SimpleLog - INFO: - Interactor 1 finished episode 406 with reward -785.364 in 200 steps
|
500 |
+
2023-06-23 23:29:46 - SimpleLog - INFO: - Interactor 0 finished episode 407 with reward -673.874 in 200 steps
|
501 |
+
2023-06-23 23:29:46 - SimpleLog - INFO: - Interactor 1 finished episode 408 with reward -840.383 in 200 steps
|
502 |
+
2023-06-23 23:29:47 - SimpleLog - INFO: - update_step: 320, online_eval_reward: -841.460
|
503 |
+
2023-06-23 23:29:47 - SimpleLog - INFO: - Interactor 0 finished episode 409 with reward -522.173 in 200 steps
|
504 |
+
2023-06-23 23:29:47 - SimpleLog - INFO: - Interactor 0 finished episode 410 with reward -392.431 in 200 steps
|
505 |
+
2023-06-23 23:29:47 - SimpleLog - INFO: - Interactor 1 finished episode 411 with reward -523.550 in 200 steps
|
506 |
+
2023-06-23 23:29:47 - SimpleLog - INFO: - Interactor 1 finished episode 412 with reward -780.707 in 200 steps
|
507 |
+
2023-06-23 23:29:47 - SimpleLog - INFO: - Interactor 0 finished episode 413 with reward -394.790 in 200 steps
|
508 |
+
2023-06-23 23:29:47 - SimpleLog - INFO: - Interactor 1 finished episode 414 with reward -908.067 in 200 steps
|
509 |
+
2023-06-23 23:29:48 - SimpleLog - INFO: - Interactor 0 finished episode 415 with reward -525.602 in 200 steps
|
510 |
+
2023-06-23 23:29:48 - SimpleLog - INFO: - Interactor 1 finished episode 416 with reward -773.933 in 200 steps
|
511 |
+
2023-06-23 23:29:48 - SimpleLog - INFO: - Interactor 0 finished episode 417 with reward -630.813 in 200 steps
|
512 |
+
2023-06-23 23:29:48 - SimpleLog - INFO: - Interactor 1 finished episode 418 with reward -706.245 in 200 steps
|
513 |
+
2023-06-23 23:29:48 - SimpleLog - INFO: - Interactor 0 finished episode 419 with reward -394.131 in 200 steps
|
514 |
+
2023-06-23 23:29:48 - SimpleLog - INFO: - Interactor 0 finished episode 420 with reward -398.713 in 200 steps
|
515 |
+
2023-06-23 23:29:48 - SimpleLog - INFO: - Interactor 1 finished episode 421 with reward -657.708 in 200 steps
|
516 |
+
2023-06-23 23:29:48 - SimpleLog - INFO: - Interactor 1 finished episode 422 with reward -389.466 in 200 steps
|
517 |
+
2023-06-23 23:29:49 - SimpleLog - INFO: - update_step: 330, online_eval_reward: -755.387
|
518 |
+
2023-06-23 23:29:49 - SimpleLog - INFO: - Interactor 0 finished episode 423 with reward -619.036 in 200 steps
|
519 |
+
2023-06-23 23:29:49 - SimpleLog - INFO: - Interactor 1 finished episode 424 with reward -753.523 in 200 steps
|
520 |
+
2023-06-23 23:29:49 - SimpleLog - INFO: - Interactor 0 finished episode 425 with reward -391.380 in 200 steps
|
521 |
+
2023-06-23 23:29:50 - SimpleLog - INFO: - Interactor 1 finished episode 426 with reward -519.378 in 200 steps
|
522 |
+
2023-06-23 23:29:50 - SimpleLog - INFO: - Interactor 0 finished episode 427 with reward -411.949 in 200 steps
|
523 |
+
2023-06-23 23:29:50 - SimpleLog - INFO: - Interactor 0 finished episode 428 with reward -487.799 in 200 steps
|
524 |
+
2023-06-23 23:29:50 - SimpleLog - INFO: - Interactor 1 finished episode 429 with reward -654.228 in 200 steps
|
525 |
+
2023-06-23 23:29:50 - SimpleLog - INFO: - Interactor 1 finished episode 430 with reward -518.676 in 200 steps
|
526 |
+
2023-06-23 23:29:50 - SimpleLog - INFO: - Interactor 0 finished episode 431 with reward -370.421 in 200 steps
|
527 |
+
2023-06-23 23:29:50 - SimpleLog - INFO: - Interactor 1 finished episode 432 with reward -521.767 in 200 steps
|
528 |
+
2023-06-23 23:29:51 - SimpleLog - INFO: - Interactor 0 finished episode 433 with reward -524.397 in 200 steps
|
529 |
+
2023-06-23 23:29:51 - SimpleLog - INFO: - Interactor 1 finished episode 434 with reward -390.198 in 200 steps
|
530 |
+
2023-06-23 23:29:51 - SimpleLog - INFO: - update_step: 340, online_eval_reward: -424.612
|
531 |
+
2023-06-23 23:29:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -424.612, save the best model!
|
532 |
+
2023-06-23 23:29:51 - SimpleLog - INFO: - Interactor 0 finished episode 435 with reward -263.223 in 200 steps
|
533 |
+
2023-06-23 23:29:51 - SimpleLog - INFO: - Interactor 1 finished episode 436 with reward -894.351 in 200 steps
|
534 |
+
2023-06-23 23:29:52 - SimpleLog - INFO: - Interactor 0 finished episode 437 with reward -393.476 in 200 steps
|
535 |
+
2023-06-23 23:29:52 - SimpleLog - INFO: - Interactor 0 finished episode 438 with reward -392.679 in 200 steps
|
536 |
+
2023-06-23 23:29:52 - SimpleLog - INFO: - Interactor 1 finished episode 439 with reward -521.002 in 200 steps
|
537 |
+
2023-06-23 23:29:52 - SimpleLog - INFO: - Interactor 1 finished episode 440 with reward -523.502 in 200 steps
|
538 |
+
2023-06-23 23:29:52 - SimpleLog - INFO: - Interactor 0 finished episode 441 with reward -1174.267 in 200 steps
|
539 |
+
2023-06-23 23:29:52 - SimpleLog - INFO: - Interactor 1 finished episode 442 with reward -1083.376 in 200 steps
|
540 |
+
2023-06-23 23:29:53 - SimpleLog - INFO: - Interactor 0 finished episode 443 with reward -584.215 in 200 steps
|
541 |
+
2023-06-23 23:29:53 - SimpleLog - INFO: - Interactor 1 finished episode 444 with reward -764.516 in 200 steps
|
542 |
+
2023-06-23 23:29:53 - SimpleLog - INFO: - Interactor 0 finished episode 445 with reward -647.459 in 200 steps
|
543 |
+
2023-06-23 23:29:53 - SimpleLog - INFO: - Interactor 0 finished episode 446 with reward -468.054 in 200 steps
|
544 |
+
2023-06-23 23:29:53 - SimpleLog - INFO: - Interactor 1 finished episode 447 with reward -902.279 in 200 steps
|
545 |
+
2023-06-23 23:29:53 - SimpleLog - INFO: - Interactor 1 finished episode 448 with reward -645.084 in 200 steps
|
546 |
+
2023-06-23 23:29:54 - SimpleLog - INFO: - update_step: 350, online_eval_reward: -635.285
|
547 |
+
2023-06-23 23:29:54 - SimpleLog - INFO: - Interactor 0 finished episode 449 with reward -514.032 in 200 steps
|
548 |
+
2023-06-23 23:29:54 - SimpleLog - INFO: - Interactor 1 finished episode 450 with reward -631.703 in 200 steps
|
549 |
+
2023-06-23 23:29:54 - SimpleLog - INFO: - Interactor 0 finished episode 451 with reward -524.422 in 200 steps
|
550 |
+
2023-06-23 23:29:54 - SimpleLog - INFO: - Interactor 1 finished episode 452 with reward -672.555 in 200 steps
|
551 |
+
2023-06-23 23:29:54 - SimpleLog - INFO: - Interactor 0 finished episode 453 with reward -387.992 in 200 steps
|
552 |
+
2023-06-23 23:29:55 - SimpleLog - INFO: - Interactor 1 finished episode 454 with reward -514.437 in 200 steps
|
553 |
+
2023-06-23 23:29:55 - SimpleLog - INFO: - Interactor 0 finished episode 455 with reward -393.917 in 200 steps
|
554 |
+
2023-06-23 23:29:55 - SimpleLog - INFO: - Interactor 0 finished episode 456 with reward -420.955 in 200 steps
|
555 |
+
2023-06-23 23:29:55 - SimpleLog - INFO: - Interactor 1 finished episode 457 with reward -648.796 in 200 steps
|
556 |
+
2023-06-23 23:29:55 - SimpleLog - INFO: - Interactor 1 finished episode 458 with reward -793.747 in 200 steps
|
557 |
+
2023-06-23 23:29:55 - SimpleLog - INFO: - Interactor 0 finished episode 459 with reward -385.825 in 200 steps
|
558 |
+
2023-06-23 23:29:55 - SimpleLog - INFO: - Interactor 1 finished episode 460 with reward -855.019 in 200 steps
|
559 |
+
2023-06-23 23:29:56 - SimpleLog - INFO: - update_step: 360, online_eval_reward: -846.796
|
560 |
+
2023-06-23 23:29:56 - SimpleLog - INFO: - Interactor 0 finished episode 461 with reward -507.891 in 200 steps
|
561 |
+
2023-06-23 23:29:56 - SimpleLog - INFO: - Interactor 1 finished episode 462 with reward -877.193 in 200 steps
|
562 |
+
2023-06-23 23:29:56 - SimpleLog - INFO: - Interactor 0 finished episode 463 with reward -525.565 in 200 steps
|
563 |
+
2023-06-23 23:29:56 - SimpleLog - INFO: - Interactor 1 finished episode 464 with reward -600.048 in 200 steps
|
564 |
+
2023-06-23 23:29:57 - SimpleLog - INFO: - Interactor 0 finished episode 465 with reward -261.655 in 200 steps
|
565 |
+
2023-06-23 23:29:57 - SimpleLog - INFO: - Interactor 0 finished episode 466 with reward -523.994 in 200 steps
|
566 |
+
2023-06-23 23:29:57 - SimpleLog - INFO: - Interactor 1 finished episode 467 with reward -784.774 in 200 steps
|
567 |
+
2023-06-23 23:29:57 - SimpleLog - INFO: - Interactor 1 finished episode 468 with reward -649.478 in 200 steps
|
568 |
+
2023-06-23 23:29:57 - SimpleLog - INFO: - Interactor 0 finished episode 469 with reward -521.083 in 200 steps
|
569 |
+
2023-06-23 23:29:57 - SimpleLog - INFO: - Interactor 1 finished episode 470 with reward -651.934 in 200 steps
|
570 |
+
2023-06-23 23:29:58 - SimpleLog - INFO: - Interactor 0 finished episode 471 with reward -260.613 in 200 steps
|
571 |
+
2023-06-23 23:29:58 - SimpleLog - INFO: - Interactor 1 finished episode 472 with reward -905.831 in 200 steps
|
572 |
+
2023-06-23 23:29:58 - SimpleLog - INFO: - update_step: 370, online_eval_reward: -754.695
|
573 |
+
2023-06-23 23:29:58 - SimpleLog - INFO: - Interactor 0 finished episode 473 with reward -393.903 in 200 steps
|
574 |
+
2023-06-23 23:29:58 - SimpleLog - INFO: - Interactor 0 finished episode 474 with reward -517.770 in 200 steps
|
575 |
+
2023-06-23 23:29:58 - SimpleLog - INFO: - Interactor 1 finished episode 475 with reward -558.586 in 200 steps
|
576 |
+
2023-06-23 23:29:59 - SimpleLog - INFO: - Interactor 1 finished episode 476 with reward -651.537 in 200 steps
|
577 |
+
2023-06-23 23:29:59 - SimpleLog - INFO: - Interactor 0 finished episode 477 with reward -617.735 in 200 steps
|
578 |
+
2023-06-23 23:29:59 - SimpleLog - INFO: - Interactor 1 finished episode 478 with reward -741.364 in 200 steps
|
579 |
+
2023-06-23 23:29:59 - SimpleLog - INFO: - Interactor 0 finished episode 479 with reward -392.718 in 200 steps
|
580 |
+
2023-06-23 23:29:59 - SimpleLog - INFO: - Interactor 1 finished episode 480 with reward -650.944 in 200 steps
|
581 |
+
2023-06-23 23:29:59 - SimpleLog - INFO: - Interactor 0 finished episode 481 with reward -337.304 in 200 steps
|
582 |
+
2023-06-23 23:30:00 - SimpleLog - INFO: - Interactor 1 finished episode 482 with reward -910.997 in 200 steps
|
583 |
+
2023-06-23 23:30:00 - SimpleLog - INFO: - Interactor 0 finished episode 483 with reward -373.592 in 200 steps
|
584 |
+
2023-06-23 23:30:00 - SimpleLog - INFO: - Interactor 0 finished episode 484 with reward -521.916 in 200 steps
|
585 |
+
2023-06-23 23:30:00 - SimpleLog - INFO: - Interactor 1 finished episode 485 with reward -521.876 in 200 steps
|
586 |
+
2023-06-23 23:30:00 - SimpleLog - INFO: - Interactor 1 finished episode 486 with reward -735.547 in 200 steps
|
587 |
+
2023-06-23 23:30:01 - SimpleLog - INFO: - update_step: 380, online_eval_reward: -735.911
|
588 |
+
2023-06-23 23:30:01 - SimpleLog - INFO: - Interactor 0 finished episode 487 with reward -526.709 in 200 steps
|
589 |
+
2023-06-23 23:30:01 - SimpleLog - INFO: - Interactor 1 finished episode 488 with reward -872.022 in 200 steps
|
590 |
+
2023-06-23 23:30:01 - SimpleLog - INFO: - Interactor 0 finished episode 489 with reward -394.488 in 200 steps
|
591 |
+
2023-06-23 23:30:01 - SimpleLog - INFO: - Interactor 1 finished episode 490 with reward -902.525 in 200 steps
|
592 |
+
2023-06-23 23:30:01 - SimpleLog - INFO: - Interactor 0 finished episode 491 with reward -392.105 in 200 steps
|
593 |
+
2023-06-23 23:30:01 - SimpleLog - INFO: - Interactor 0 finished episode 492 with reward -524.270 in 200 steps
|
594 |
+
2023-06-23 23:30:01 - SimpleLog - INFO: - Interactor 1 finished episode 493 with reward -886.782 in 200 steps
|
595 |
+
2023-06-23 23:30:02 - SimpleLog - INFO: - Interactor 1 finished episode 494 with reward -907.321 in 200 steps
|
596 |
+
2023-06-23 23:30:02 - SimpleLog - INFO: - Interactor 0 finished episode 495 with reward -393.800 in 200 steps
|
597 |
+
2023-06-23 23:30:02 - SimpleLog - INFO: - Interactor 1 finished episode 496 with reward -906.613 in 200 steps
|
598 |
+
2023-06-23 23:30:02 - SimpleLog - INFO: - Interactor 0 finished episode 497 with reward -518.960 in 200 steps
|
599 |
+
2023-06-23 23:30:02 - SimpleLog - INFO: - Interactor 1 finished episode 498 with reward -648.317 in 200 steps
|
600 |
+
2023-06-23 23:30:03 - SimpleLog - INFO: - update_step: 390, online_eval_reward: -629.548
|
601 |
+
2023-06-23 23:30:03 - SimpleLog - INFO: - Interactor 0 finished episode 499 with reward -385.421 in 200 steps
|
602 |
+
2023-06-23 23:30:03 - SimpleLog - INFO: - Interactor 1 finished episode 500 with reward -625.152 in 200 steps
|
603 |
+
2023-06-23 23:30:03 - SimpleLog - INFO: - Finish training! Time cost: 90.839 s
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/10
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/100
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d8413d47624eb3aba70616f411878a4a90ba393ebe02704cda3d35372e34fa8
|
3 |
+
size 13451
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/110
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/120
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/130
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/140
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/150
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/160
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/170
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/180
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/190
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/20
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/200
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97c7c004bfea9a3aa16bf8bf029d1434956a03e323e1fadf82f9d4f7f6ed1abd
|
3 |
+
size 13451
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/210
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/220
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/230
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/240
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/250
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/260
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/270
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/280
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/290
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/30
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/300
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f69d3dfa226dbf01df39efb2ab7869106e99448022e32ffcaec79f6ff23d6dfa
|
3 |
+
size 13451
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/310
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/320
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/330
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/340
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/350
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/360
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/370
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/380
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/390
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/40
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/50
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/60
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/70
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/80
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/90
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/models/best
ADDED
Binary file (13.5 kB). View file
|
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/tb_logs/interact/events.out.tfevents.1687534112.ML3090.1059326.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14119a4ace626bc7c71442a4bebc45095230bdb6049c7ee959979417600b3b71
|
3 |
+
size 49786
|
ClassControl/Pendulum-v1/Train_Pendulum-v1_A2C_20230623-232832/tb_logs/policy/events.out.tfevents.1687534112.ML3090.1059326.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50b87dd3856ae02d10d99c4749e838b914170e09ea05f3266a0dd940c3b016d3
|
3 |
+
size 66392
|