{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8401288986206055, "min": 1.748769760131836, "max": 3.2957043647766113, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36331.50390625, "min": 28458.958984375, "max": 152256.328125, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 37.48461538461538, "min": 33.28378378378378, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19492.0, "min": 15300.0, "max": 26408.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1475.635204651017, "min": 1187.82528421093, "max": 1527.4238936954232, "count": 989 }, "SoccerTwos.Self-play.ELO.sum": { "value": 383665.1532092644, "min": 2381.097975046616, "max": 441831.0423995003, "count": 989 }, "SoccerTwos.Step.mean": { "value": 9999996.0, "min": 9222.0, "max": 9999996.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999996.0, "min": 9222.0, "max": 9999996.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0018012766959145665, "min": -0.12405411154031754, "max": 0.12426542490720749, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.4683319330215454, "min": -27.54001235961914, "max": 27.272319793701172, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00776406517252326, "min": -0.1302955448627472, "max": 0.12741929292678833, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.0186569690704346, "min": -28.925609588623047, "max": 27.275447845458984, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.010678462798778827, "min": -0.5646769221012409, "max": 0.549038093714487, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.776400327682495, "min": -66.26320040225983, "max": 79.14160007238388, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.010678462798778827, "min": -0.5646769221012409, "max": 0.549038093714487, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.776400327682495, "min": -66.26320040225983, "max": 79.14160007238388, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016107048803112572, "min": 0.011318811624854182, "max": 0.023032417175515244, "count": 317 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016107048803112572, "min": 0.011318811624854182, "max": 0.023032417175515244, "count": 317 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07700270016988119, "min": 0.00043191949185307347, "max": 0.08238112115197711, "count": 317 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07700270016988119, "min": 0.00043191949185307347, "max": 0.08238112115197711, "count": 317 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08115983572271135, "min": 0.0004307039562263526, "max": 0.08558417591783736, "count": 317 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08115983572271135, "min": 0.0004307039562263526, "max": 0.08558417591783736, "count": 317 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00040000000000000013, "min": 0.0004, "max": 0.00040000000000000013, "count": 317 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00040000000000000013, "min": 0.0004, "max": 0.00040000000000000013, "count": 317 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999993, "min": 0.19999999999999993, "max": 0.19999999999999998, "count": 317 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999993, "min": 0.19999999999999993, "max": 0.19999999999999998, "count": 317 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 317 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 317 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1740285677", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/leandrosartini/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwosR --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740300627" }, "total": 13728.469551967999, "count": 1, "self": 0.2702088289988751, "children": { "run_training.setup": { "total": 0.013737434999711695, "count": 1, "self": 0.013737434999711695 }, "TrainerController.start_learning": { "total": 13728.185605704, "count": 1, "self": 8.488870302846408, "children": { "TrainerController._reset_env": { "total": 2.342965550016743, "count": 50, "self": 2.342965550016743 }, "TrainerController.advance": { "total": 13717.262332993136, "count": 699870, "self": 8.433981400963603, "children": { "env_step": { "total": 10742.564940080289, "count": 699870, "self": 7150.7972829954015, "children": { "SubprocessEnvManager._take_step": { "total": 3586.353386144039, "count": 699870, "self": 54.62267443440578, "children": { "TorchPolicy.evaluate": { "total": 3531.7307117096334, "count": 1258982, "self": 3531.7307117096334 } } }, "workers": { "total": 5.414270940847928, "count": 699870, "self": 0.0, "children": { "worker_root": { "total": 13710.248531242893, "count": 699870, "is_parallel": true, "self": 7500.461064878009, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002051157000096282, "count": 2, "is_parallel": true, "self": 0.0005986070027574897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014525499973387923, "count": 8, "is_parallel": true, "self": 0.0014525499973387923 } } }, "UnityEnvironment.step": { "total": 0.023481369000364793, "count": 1, "is_parallel": true, "self": 0.0004319930030760588, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000267138999333838, "count": 1, "is_parallel": true, "self": 0.000267138999333838 }, "communicator.exchange": { "total": 0.02132947999962198, "count": 1, "is_parallel": true, "self": 0.02132947999962198 }, "steps_from_proto": { "total": 0.0014527569983329158, "count": 2, "is_parallel": true, "self": 0.0002980149947688915, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011547420035640243, "count": 8, "is_parallel": true, "self": 0.0011547420035640243 } } } } } } }, "UnityEnvironment.step": { "total": 6209.745126282913, "count": 699869, "is_parallel": true, "self": 201.9172636795265, "children": { "UnityEnvironment._generate_step_input": { "total": 118.71616534273744, "count": 699869, "is_parallel": true, "self": 118.71616534273744 }, "communicator.exchange": { "total": 5295.104212875562, "count": 699869, "is_parallel": true, "self": 5295.104212875562 }, "steps_from_proto": { "total": 594.0074843850871, "count": 1399738, "is_parallel": true, "self": 122.34024345268517, "children": { "_process_rank_one_or_two_observation": { "total": 471.6672409324019, "count": 5598952, "is_parallel": true, "self": 471.6672409324019 } } } } }, "steps_from_proto": { "total": 0.042340081970905885, "count": 98, "is_parallel": true, "self": 0.008750974950089585, "children": { "_process_rank_one_or_two_observation": { "total": 0.0335891070208163, "count": 392, "is_parallel": true, "self": 0.0335891070208163 } } } } } } } } }, "trainer_advance": { "total": 2966.2634115118835, "count": 699870, "self": 58.89060738813896, "children": { "process_trajectory": { "total": 1796.2287291927132, "count": 699870, "self": 1794.1863172777175, "children": { "RLTrainer._checkpoint": { "total": 2.0424119149956823, "count": 20, "self": 2.0424119149956823 } } }, "_update_policy": { "total": 1111.1440749310314, "count": 317, "self": 616.2691592630508, "children": { "TorchPOCAOptimizer.update": { "total": 494.87491566798053, "count": 14289, "self": 494.87491566798053 } } } } } } }, "trainer_threads": { "total": 3.770001058001071e-07, "count": 1, "self": 3.770001058001071e-07 }, "TrainerController._save_models": { "total": 0.09143648100143764, "count": 1, "self": 0.0008594000028097071, "children": { "RLTrainer._checkpoint": { "total": 0.09057708099862793, "count": 1, "self": 0.09057708099862793 } } } } } } }