{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4101879596710205, "min": 1.332898497581482, "max": 3.2957260608673096, "count": 4999 }, "SoccerTwos.Policy.Entropy.sum": { "value": 26082.8359375, "min": 22169.224609375, "max": 136329.171875, "count": 4999 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 66.66666666666667, "min": 41.96521739130435, "max": 999.0, "count": 4999 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19200.0, "min": 16408.0, "max": 31968.0, "count": 4999 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1573.4164997834623, "min": 1186.6917021576141, "max": 1669.2404820206275, "count": 4982 }, "SoccerTwos.Self-play.ELO.sum": { "value": 226571.9759688186, "min": 2385.2321208535777, "max": 374084.48853586055, "count": 4982 }, "SoccerTwos.Step.mean": { "value": 49999855.0, "min": 9300.0, "max": 49999855.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999855.0, "min": 9300.0, "max": 49999855.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.013657771982252598, "min": -0.1438334584236145, "max": 0.15958504378795624, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.980376958847046, "min": -22.568527221679688, "max": 22.907155990600586, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.013520356267690659, "min": -0.14296653866767883, "max": 0.16129207611083984, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.960451602935791, "min": -23.43581199645996, "max": 23.799938201904297, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0393379310081745, "min": -0.7995407404722991, "max": 0.46243846072600436, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.703999996185303, "min": -68.21680003404617, "max": 62.27440017461777, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0393379310081745, "min": -0.7995407404722991, "max": 0.46243846072600436, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.703999996185303, "min": -68.21680003404617, "max": 62.27440017461777, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01482800834637601, "min": 0.009856824992554417, "max": 0.025938480199935537, "count": 2423 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01482800834637601, "min": 0.009856824992554417, "max": 0.025938480199935537, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09889063363273938, "min": 9.758156763079266e-05, "max": 0.1255539710323016, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09889063363273938, "min": 9.758156763079266e-05, "max": 0.1255539710323016, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09956269562244416, "min": 9.800574043765664e-05, "max": 0.12865835502743722, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09956269562244416, "min": 9.800574043765664e-05, "max": 0.12865835502743722, "count": 2423 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2423 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2423 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704379062", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/external-rosia/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704510825" }, "total": 131762.20611413568, "count": 1, "self": 0.3711693393997848, "children": { "run_training.setup": { "total": 0.017532712314277887, "count": 1, "self": 0.017532712314277887 }, "TrainerController.start_learning": { "total": 131761.81741208397, "count": 1, "self": 46.809156748466194, "children": { "TrainerController._reset_env": { "total": 9.621022965759039, "count": 250, "self": 9.621022965759039 }, "TrainerController.advance": { "total": 131705.24929426098, "count": 3442754, "self": 47.45445933472365, "children": { "env_step": { "total": 115003.77731117373, "count": 3442754, "self": 98212.8201123355, "children": { "SubprocessEnvManager._take_step": { "total": 16761.12573245028, "count": 3442754, "self": 363.5279528698884, "children": { "TorchPolicy.evaluate": { "total": 16397.597779580392, "count": 6282076, "self": 16397.597779580392 } } }, "workers": { "total": 29.831466387957335, "count": 3442754, "self": 0.0, "children": { "worker_root": { "total": 131569.22664459608, "count": 3442754, "is_parallel": true, "self": 41519.95227844734, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0070021990686655045, "count": 2, "is_parallel": true, "self": 0.0016497056931257248, "children": { "_process_rank_one_or_two_observation": { "total": 0.00535249337553978, "count": 8, "is_parallel": true, "self": 0.00535249337553978 } } }, "UnityEnvironment.step": { "total": 0.03543186094611883, "count": 1, "is_parallel": true, "self": 0.00166629021987319, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0012752348557114601, "count": 1, "is_parallel": true, "self": 0.0012752348557114601 }, "communicator.exchange": { "total": 0.027705941814929247, "count": 1, "is_parallel": true, "self": 0.027705941814929247 }, "steps_from_proto": { "total": 0.004784394055604935, "count": 2, "is_parallel": true, "self": 0.0009212824515998363, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038631116040050983, "count": 8, "is_parallel": true, "self": 0.0038631116040050983 } } } } } } }, "UnityEnvironment.step": { "total": 90048.13488004962, "count": 3442753, "is_parallel": true, "self": 5340.922976269387, "children": { "UnityEnvironment._generate_step_input": { "total": 3693.6092337705195, "count": 3442753, "is_parallel": true, "self": 3693.6092337705195 }, "communicator.exchange": { "total": 65930.58416355588, "count": 3442753, "is_parallel": true, "self": 65930.58416355588 }, "steps_from_proto": { "total": 15083.018506453838, "count": 6885506, "is_parallel": true, "self": 2741.9420437025838, "children": { "_process_rank_one_or_two_observation": { "total": 12341.076462751254, "count": 27542024, "is_parallel": true, "self": 12341.076462751254 } } } } }, "steps_from_proto": { "total": 1.13948609912768, "count": 498, "is_parallel": true, "self": 0.20297252899035811, "children": { "_process_rank_one_or_two_observation": { "total": 0.936513570137322, "count": 1992, "is_parallel": true, "self": 0.936513570137322 } } } } } } } } }, "trainer_advance": { "total": 16654.017523752525, "count": 3442754, "self": 367.28710281895474, "children": { "process_trajectory": { "total": 7652.751466519665, "count": 3442754, "self": 7638.177386100404, "children": { "RLTrainer._checkpoint": { "total": 14.574080419261009, "count": 100, "self": 14.574080419261009 } } }, "_update_policy": { "total": 8633.978954413906, "count": 2423, "self": 5363.2341864197515, "children": { "TorchPOCAOptimizer.update": { "total": 3270.7447679941542, "count": 72702, "self": 3270.7447679941542 } } } } } } }, "trainer_threads": { "total": 8.149072527885437e-07, "count": 1, "self": 8.149072527885437e-07 }, "TrainerController._save_models": { "total": 0.13793729385361075, "count": 1, "self": 0.001317872665822506, "children": { "RLTrainer._checkpoint": { "total": 0.13661942118778825, "count": 1, "self": 0.13661942118778825 } } } } } } }