{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.949866771697998, "min": 1.9038461446762085, "max": 3.295717477798462, "count": 515 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38435.7734375, "min": 22307.6015625, "max": 146835.03125, "count": 515 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.714285714285715, "min": 39.853658536585364, "max": 999.0, "count": 515 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19488.0, "min": 9716.0, "max": 30256.0, "count": 515 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1494.4706126619362, "min": 1187.6475644305722, "max": 1520.4729102408817, "count": 498 }, "SoccerTwos.Self-play.ELO.sum": { "value": 292916.2400817395, "min": 2375.295128861145, "max": 358081.4128658451, "count": 498 }, "SoccerTwos.Step.mean": { "value": 5149984.0, "min": 9146.0, "max": 5149984.0, "count": 515 }, "SoccerTwos.Step.sum": { "value": 5149984.0, "min": 9146.0, "max": 5149984.0, "count": 515 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.023766376078128815, "min": -0.11065083742141724, "max": 0.14663831889629364, "count": 515 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.634443283081055, "min": -22.462120056152344, "max": 26.81417465209961, "count": 515 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02699751779437065, "min": -0.10361790657043457, "max": 0.15298697352409363, "count": 515 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.2645158767700195, "min": -21.034435272216797, "max": 27.09004020690918, "count": 515 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 515 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 515 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.01454769158974672, "min": -0.7776833325624466, "max": 0.4368000030517578, "count": 515 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.8367998600006104, "min": -52.7460001707077, "max": 48.936999917030334, "count": 515 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.01454769158974672, "min": -0.7776833325624466, "max": 0.4368000030517578, "count": 515 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.8367998600006104, "min": -52.7460001707077, "max": 48.936999917030334, "count": 515 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 515 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 515 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016999113700391415, "min": 0.010449916155387958, "max": 0.02299387886111314, "count": 246 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016999113700391415, "min": 0.010449916155387958, "max": 0.02299387886111314, "count": 246 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11672106881936391, "min": 1.5938594545635474e-05, "max": 0.13033197994033496, "count": 246 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11672106881936391, "min": 1.5938594545635474e-05, "max": 0.13033197994033496, "count": 246 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11834554622570674, "min": 1.7589039271115325e-05, "max": 0.1332785926759243, "count": 246 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11834554622570674, "min": 1.7589039271115325e-05, "max": 0.1332785926759243, "count": 246 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 246 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 246 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 246 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 246 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 246 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 246 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679325708", "python_version": "3.9.13 | packaged by conda-forge | (main, May 27 2022, 16:56:21) \n[GCC 10.3.0]", "command_line_arguments": "/opt/saturncloud/envs/saturn/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos --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", "numpy_version": "1.21.2", "end_time_seconds": "1679335265" }, "total": 9556.705615911, "count": 1, "self": 0.3238894040005107, "children": { "run_training.setup": { "total": 0.06776886199997989, "count": 1, "self": 0.06776886199997989 }, "TrainerController.start_learning": { "total": 9556.313957645, "count": 1, "self": 9.010932760758806, "children": { "TrainerController._reset_env": { "total": 4.471771796998951, "count": 26, "self": 4.471771796998951 }, "TrainerController.advance": { "total": 9542.569501911243, "count": 347881, "self": 9.548699004579248, "children": { "env_step": { "total": 7338.147268633859, "count": 347881, "self": 5696.228293102238, "children": { "SubprocessEnvManager._take_step": { "total": 1636.7174432656486, "count": 347881, "self": 52.86974630196778, "children": { "TorchPolicy.evaluate": { "total": 1583.8476969636808, "count": 652240, "self": 1583.8476969636808 } } }, "workers": { "total": 5.2015322659726735, "count": 347881, "self": 0.0, "children": { "worker_root": { "total": 9539.849482706646, "count": 347881, "is_parallel": true, "self": 4824.486650240596, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032336990000203514, "count": 2, "is_parallel": true, "self": 0.0008544720000713824, "children": { "_process_rank_one_or_two_observation": { "total": 0.002379226999948969, "count": 8, "is_parallel": true, "self": 0.002379226999948969 } } }, "UnityEnvironment.step": { "total": 0.03683238299998948, "count": 1, "is_parallel": true, "self": 0.000967803999969874, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048257299999932, "count": 1, "is_parallel": true, "self": 0.00048257299999932 }, "communicator.exchange": { "total": 0.03196520099999134, "count": 1, "is_parallel": true, "self": 0.03196520099999134 }, "steps_from_proto": { "total": 0.003416805000028944, "count": 2, "is_parallel": true, "self": 0.0006858429999283544, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027309620001005896, "count": 8, "is_parallel": true, "self": 0.0027309620001005896 } } } } } } }, "UnityEnvironment.step": { "total": 4715.31175617305, "count": 347880, "is_parallel": true, "self": 228.14410371560098, "children": { "UnityEnvironment._generate_step_input": { "total": 159.77012413482356, "count": 347880, "is_parallel": true, "self": 159.77012413482356 }, "communicator.exchange": { "total": 3517.11550017691, "count": 347880, "is_parallel": true, "self": 3517.11550017691 }, "steps_from_proto": { "total": 810.2820281457156, "count": 695760, "is_parallel": true, "self": 162.34399068611003, "children": { "_process_rank_one_or_two_observation": { "total": 647.9380374596055, "count": 2783040, "is_parallel": true, "self": 647.9380374596055 } } } } }, "steps_from_proto": { "total": 0.05107629300050576, "count": 50, "is_parallel": true, "self": 0.010999812994782587, "children": { "_process_rank_one_or_two_observation": { "total": 0.04007648000572317, "count": 200, "is_parallel": true, "self": 0.04007648000572317 } } } } } } } } }, "trainer_advance": { "total": 2194.873534272803, "count": 347881, "self": 67.65676349741716, "children": { "process_trajectory": { "total": 809.2768928793882, "count": 347881, "self": 806.6027529233868, "children": { "RLTrainer._checkpoint": { "total": 2.6741399560014543, "count": 10, "self": 2.6741399560014543 } } }, "_update_policy": { "total": 1317.9398778959976, "count": 246, "self": 819.1573420940358, "children": { "TorchPOCAOptimizer.update": { "total": 498.7825358019617, "count": 7383, "self": 498.7825358019617 } } } } } } }, "trainer_threads": { "total": 8.369988790946081e-07, "count": 1, "self": 8.369988790946081e-07 }, "TrainerController._save_models": { "total": 0.2617503389992635, "count": 1, "self": 0.0015195359992503654, "children": { "RLTrainer._checkpoint": { "total": 0.2602308030000131, "count": 1, "self": 0.2602308030000131 } } } } } } }