{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7128549814224243, "min": 1.5581896305084229, "max": 3.295715570449829, "count": 1050 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32448.32421875, "min": 25265.078125, "max": 111096.9609375, "count": 1050 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 81.13333333333334, "min": 38.09230769230769, "max": 999.0, "count": 1050 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19472.0, "min": 12372.0, "max": 28620.0, "count": 1050 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1580.6771237852813, "min": 1202.050846343015, "max": 1597.4136494576903, "count": 1046 }, "SoccerTwos.Self-play.ELO.sum": { "value": 189681.25485423376, "min": 2405.569774810032, "max": 399700.56926728017, "count": 1046 }, "SoccerTwos.Step.mean": { "value": 10499931.0, "min": 9328.0, "max": 10499931.0, "count": 1050 }, "SoccerTwos.Step.sum": { "value": 10499931.0, "min": 9328.0, "max": 10499931.0, "count": 1050 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04390044882893562, "min": -0.1101670041680336, "max": 0.18953292071819305, "count": 1050 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.268054008483887, "min": -22.58423614501953, "max": 35.442657470703125, "count": 1050 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.044188063591718674, "min": -0.1123552992939949, "max": 0.1864115595817566, "count": 1050 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.302567481994629, "min": -23.205352783203125, "max": 34.85896301269531, "count": 1050 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1050 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1050 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.3271366665760676, "min": -0.5193191487738427, "max": 0.5675200040638447, "count": 1050 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -39.25639998912811, "min": -62.24919992685318, "max": 80.7293998003006, "count": 1050 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3271366665760676, "min": -0.5193191487738427, "max": 0.5675200040638447, "count": 1050 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -39.25639998912811, "min": -62.24919992685318, "max": 80.7293998003006, "count": 1050 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1050 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1050 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014911501641230037, "min": 0.009128271920296053, "max": 0.02562875791142384, "count": 508 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014911501641230037, "min": 0.009128271920296053, "max": 0.02562875791142384, "count": 508 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08880021100242932, "min": 3.157012167018062e-05, "max": 0.1292675219476223, "count": 508 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08880021100242932, "min": 3.157012167018062e-05, "max": 0.1292675219476223, "count": 508 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08974442308147748, "min": 3.250128799360634e-05, "max": 0.13150458385547, "count": 508 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08974442308147748, "min": 3.250128799360634e-05, "max": 0.13150458385547, "count": 508 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 508 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 508 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 508 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 508 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 508 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 508 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675601256", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/sebas/miniconda3/envs/RL-Soccer/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1675615910" }, "total": 14653.31670713611, "count": 1, "self": 0.21818605531007051, "children": { "run_training.setup": { "total": 0.007037502713501453, "count": 1, "self": 0.007037502713501453 }, "TrainerController.start_learning": { "total": 14653.091483578086, "count": 1, "self": 11.077687626704574, "children": { "TrainerController._reset_env": { "total": 3.068363525904715, "count": 53, "self": 3.068363525904715 }, "TrainerController.advance": { "total": 14638.802216160111, "count": 728323, "self": 11.075973456725478, "children": { "env_step": { "total": 11227.207636157982, "count": 728323, "self": 7498.405159624293, "children": { "SubprocessEnvManager._take_step": { "total": 3721.7012588111684, "count": 728323, "self": 55.63635611347854, "children": { "TorchPolicy.evaluate": { "total": 3666.06490269769, "count": 1320080, "self": 3666.06490269769 } } }, "workers": { "total": 7.101217722520232, "count": 728323, "self": 0.0, "children": { "worker_root": { "total": 14638.376493416727, "count": 728323, "is_parallel": true, "self": 8353.074667340145, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015499358996748924, "count": 2, "is_parallel": true, "self": 0.0003869198262691498, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011630160734057426, "count": 8, "is_parallel": true, "self": 0.0011630160734057426 } } }, "UnityEnvironment.step": { "total": 0.018731185235083103, "count": 1, "is_parallel": true, "self": 0.000395345501601696, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002985699102282524, "count": 1, "is_parallel": true, "self": 0.0002985699102282524 }, "communicator.exchange": { "total": 0.01680014841258526, "count": 1, "is_parallel": true, "self": 0.01680014841258526 }, "steps_from_proto": { "total": 0.0012371214106678963, "count": 2, "is_parallel": true, "self": 0.0002609100192785263, "children": { "_process_rank_one_or_two_observation": { "total": 0.00097621139138937, "count": 8, "is_parallel": true, "self": 0.00097621139138937 } } } } } } }, "UnityEnvironment.step": { "total": 6285.230786429718, "count": 728322, "is_parallel": true, "self": 358.0044696861878, "children": { "UnityEnvironment._generate_step_input": { "total": 183.75890273228288, "count": 728322, "is_parallel": true, "self": 183.75890273228288 }, "communicator.exchange": { "total": 4794.081561687402, "count": 728322, "is_parallel": true, "self": 4794.081561687402 }, "steps_from_proto": { "total": 949.385852323845, "count": 1456644, "is_parallel": true, "self": 175.97760394308716, "children": { "_process_rank_one_or_two_observation": { "total": 773.4082483807579, "count": 5826576, "is_parallel": true, "self": 773.4082483807579 } } } } }, "steps_from_proto": { "total": 0.07103964686393738, "count": 104, "is_parallel": true, "self": 0.013023688457906246, "children": { "_process_rank_one_or_two_observation": { "total": 0.05801595840603113, "count": 416, "is_parallel": true, "self": 0.05801595840603113 } } } } } } } } }, "trainer_advance": { "total": 3400.5186065454036, "count": 728323, "self": 75.86250586993992, "children": { "process_trajectory": { "total": 1681.5410244958475, "count": 728323, "self": 1678.1162326131016, "children": { "RLTrainer._checkpoint": { "total": 3.4247918827459216, "count": 21, "self": 3.4247918827459216 } } }, "_update_policy": { "total": 1643.1150761796162, "count": 508, "self": 992.5698665492237, "children": { "TorchPOCAOptimizer.update": { "total": 650.5452096303925, "count": 15246, "self": 650.5452096303925 } } } } } } }, "trainer_threads": { "total": 5.718320608139038e-07, "count": 1, "self": 5.718320608139038e-07 }, "TrainerController._save_models": { "total": 0.14321569353342056, "count": 1, "self": 0.0009191790595650673, "children": { "RLTrainer._checkpoint": { "total": 0.1422965144738555, "count": 1, "self": 0.1422965144738555 } } } } } } }