{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1853787899017334, "min": 3.1321542263031006, "max": 3.295640230178833, "count": 55 }, "SoccerTwos.Policy.Entropy.sum": { "value": 85724.9140625, "min": 18404.51953125, "max": 105460.453125, "count": 55 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 360.8, "min": 233.56521739130434, "max": 999.0, "count": 55 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21648.0, "min": 17612.0, "max": 23816.0, "count": 55 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1235.6966781131266, "min": 1193.9849330349607, "max": 1235.6966781131266, "count": 53 }, "SoccerTwos.Self-play.ELO.sum": { "value": 34599.506987167544, "min": 2388.421744919647, "max": 56583.659072376024, "count": 53 }, "SoccerTwos.Step.mean": { "value": 549998.0, "min": 9924.0, "max": 549998.0, "count": 55 }, "SoccerTwos.Step.sum": { "value": 549998.0, "min": 9924.0, "max": 549998.0, "count": 55 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.016695523634552956, "min": -0.009290765970945358, "max": 0.07515978068113327, "count": 55 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.5008656978607178, "min": -0.3065952658653259, "max": 1.0521931648254395, "count": 55 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.01842910423874855, "min": -0.009097704663872719, "max": 0.07520028203725815, "count": 55 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.5528731346130371, "min": -0.300224244594574, "max": 1.1129671335220337, "count": 55 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 55 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 55 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.5275066653887431, "min": -0.6299000016103188, "max": 0.5275066653887431, "count": 55 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 15.825199961662292, "min": -15.117600038647652, "max": 15.825199961662292, "count": 55 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.5275066653887431, "min": -0.6299000016103188, "max": 0.5275066653887431, "count": 55 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 15.825199961662292, "min": -15.117600038647652, "max": 15.825199961662292, "count": 55 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 55 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 55 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019107229733435815, "min": 0.011625102110459314, "max": 0.023824517099031557, "count": 25 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019107229733435815, "min": 0.011625102110459314, "max": 0.023824517099031557, "count": 25 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.019781758605192105, "min": 0.0018005522550083696, "max": 0.019781758605192105, "count": 25 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.019781758605192105, "min": 0.0018005522550083696, "max": 0.019781758605192105, "count": 25 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.02071026973426342, "min": 0.0018095454666763543, "max": 0.02071026973426342, "count": 25 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.02071026973426342, "min": 0.0018095454666763543, "max": 0.02071026973426342, "count": 25 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 25 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 25 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 25 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 25 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 25 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690226164", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\yojit\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1690228555" }, "total": 2391.4622449000003, "count": 1, "self": 0.3056692000000112, "children": { "run_training.setup": { "total": 0.17043860000000022, "count": 1, "self": 0.17043860000000022 }, "TrainerController.start_learning": { "total": 2390.9861371, "count": 1, "self": 1.1522503999890432, "children": { "TrainerController._reset_env": { "total": 4.933811299999984, "count": 3, "self": 4.933811299999984 }, "TrainerController.advance": { "total": 2384.663659600011, "count": 36000, "self": 1.3310645000224213, "children": { "env_step": { "total": 921.8023372999942, "count": 36000, "self": 715.4007014999893, "children": { "SubprocessEnvManager._take_step": { "total": 205.67426330000313, "count": 36000, "self": 7.900247900007798, "children": { "TorchPolicy.evaluate": { "total": 197.77401539999533, "count": 71210, "self": 197.77401539999533 } } }, "workers": { "total": 0.727372500001751, "count": 36000, "self": 0.0, "children": { "worker_root": { "total": 2349.111099200014, "count": 36000, "is_parallel": true, "self": 1774.1064614000106, "children": { "steps_from_proto": { "total": 0.006796600000422259, "count": 6, "is_parallel": true, "self": 0.00136760000067504, "children": { "_process_rank_one_or_two_observation": { "total": 0.005428999999747219, "count": 24, "is_parallel": true, "self": 0.005428999999747219 } } }, "UnityEnvironment.step": { "total": 574.997841200003, "count": 36000, "is_parallel": true, "self": 32.59274699997536, "children": { "UnityEnvironment._generate_step_input": { "total": 24.573396800002243, "count": 36000, "is_parallel": true, "self": 24.573396800002243 }, "communicator.exchange": { "total": 411.39709200000976, "count": 36000, "is_parallel": true, "self": 411.39709200000976 }, "steps_from_proto": { "total": 106.43460540001567, "count": 72000, "is_parallel": true, "self": 21.500849300048472, "children": { "_process_rank_one_or_two_observation": { "total": 84.9337560999672, "count": 288000, "is_parallel": true, "self": 84.9337560999672 } } } } } } } } } } }, "trainer_advance": { "total": 1461.5302577999944, "count": 36000, "self": 8.366181699980416, "children": { "process_trajectory": { "total": 194.8513073000147, "count": 36000, "self": 194.18469420001452, "children": { "RLTrainer._checkpoint": { "total": 0.6666131000001769, "count": 1, "self": 0.6666131000001769 } } }, "_update_policy": { "total": 1258.3127687999993, "count": 26, "self": 116.67866579999577, "children": { "TorchPOCAOptimizer.update": { "total": 1141.6341030000035, "count": 770, "self": 1141.6341030000035 } } } } } } }, "trainer_threads": { "total": 3.200000264769187e-06, "count": 1, "self": 3.200000264769187e-06 }, "TrainerController._save_models": { "total": 0.23641259999976683, "count": 1, "self": 0.01481499999999869, "children": { "RLTrainer._checkpoint": { "total": 0.22159759999976814, "count": 1, "self": 0.22159759999976814 } } } } } } }