{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5232912302017212, "min": 1.4524929523468018, "max": 3.295693874359131, "count": 2726 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32074.419921875, "min": 24522.302734375, "max": 105462.203125, "count": 2726 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 74.84848484848484, "min": 42.902654867256636, "max": 999.0, "count": 2726 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19760.0, "min": 928.0, "max": 31000.0, "count": 2726 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1665.4253460478635, "min": 1199.496323851656, "max": 1732.2596207475895, "count": 2719 }, "SoccerTwos.Self-play.ELO.sum": { "value": 219836.145678318, "min": 2399.988520266327, "max": 354722.7644571557, "count": 2719 }, "SoccerTwos.Step.mean": { "value": 27259922.0, "min": 9140.0, "max": 27259922.0, "count": 2726 }, "SoccerTwos.Step.sum": { "value": 27259922.0, "min": 9140.0, "max": 27259922.0, "count": 2726 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.003984358161687851, "min": -0.13387973606586456, "max": 0.23543542623519897, "count": 2726 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.5259352922439575, "min": -21.22277069091797, "max": 24.327011108398438, "count": 2726 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0031756118405610323, "min": -0.12983833253383636, "max": 0.23879003524780273, "count": 2726 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.4191807508468628, "min": -21.19337272644043, "max": 24.70865821838379, "count": 2726 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2726 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2726 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.019033331762660633, "min": -0.6666666666666666, "max": 0.47401355989908767, "count": 2726 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.5123997926712036, "min": -55.39319986104965, "max": 64.57020002603531, "count": 2726 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.019033331762660633, "min": -0.6666666666666666, "max": 0.47401355989908767, "count": 2726 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.5123997926712036, "min": -55.39319986104965, "max": 64.57020002603531, "count": 2726 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2726 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2726 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01947002433395634, "min": 0.009203283006111935, "max": 0.0286280690090886, "count": 1321 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01947002433395634, "min": 0.009203283006111935, "max": 0.0286280690090886, "count": 1321 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08533640603224436, "min": 0.0005722908213404783, "max": 0.11490969508886337, "count": 1321 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08533640603224436, "min": 0.0005722908213404783, "max": 0.11490969508886337, "count": 1321 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08664804895718893, "min": 0.0005702611568267457, "max": 0.11693569918473562, "count": 1321 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08664804895718893, "min": 0.0005702611568267457, "max": 0.11693569918473562, "count": 1321 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1321 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1321 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1321 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1321 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1321 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1321 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1743065613", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/samrito/anaconda3/envs/drl_hf/bin/mlagents-learn ./SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --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": "1743087033" }, "total": 21419.806948977057, "count": 1, "self": 0.06077698618173599, "children": { "run_training.setup": { "total": 0.010219641961157322, "count": 1, "self": 0.010219641961157322 }, "TrainerController.start_learning": { "total": 21419.735952348914, "count": 1, "self": 19.17918024607934, "children": { "TrainerController._reset_env": { "total": 2.262196201365441, "count": 110, "self": 2.262196201365441 }, "TrainerController.advance": { "total": 21398.188616118394, "count": 1865510, "self": 20.750042891595513, "children": { "env_step": { "total": 16269.669052127749, "count": 1865510, "self": 11917.53296902799, "children": { "SubprocessEnvManager._take_step": { "total": 4339.913956762059, "count": 1865510, "self": 126.54519875603728, "children": { "TorchPolicy.evaluate": { "total": 4213.368758006021, "count": 3422492, "self": 4213.368758006021 } } }, "workers": { "total": 12.222126337699592, "count": 1865510, "self": 0.0, "children": { "worker_root": { "total": 21396.307301682886, "count": 1865510, "is_parallel": true, "self": 11680.562945507467, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012204230297356844, "count": 2, "is_parallel": true, "self": 0.0002994914539158344, "children": { "_process_rank_one_or_two_observation": { "total": 0.00092093157581985, "count": 8, "is_parallel": true, "self": 0.00092093157581985 } } }, "UnityEnvironment.step": { "total": 0.015100114047527313, "count": 1, "is_parallel": true, "self": 0.00042400602251291275, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021301698870956898, "count": 1, "is_parallel": true, "self": 0.00021301698870956898 }, "communicator.exchange": { "total": 0.013068980071693659, "count": 1, "is_parallel": true, "self": 0.013068980071693659 }, "steps_from_proto": { "total": 0.0013941109646111727, "count": 2, "is_parallel": true, "self": 0.00030786730349063873, "children": { "_process_rank_one_or_two_observation": { "total": 0.001086243661120534, "count": 8, "is_parallel": true, "self": 0.001086243661120534 } } } } } } }, "UnityEnvironment.step": { "total": 9715.656926060328, "count": 1865509, "is_parallel": true, "self": 522.2820660541765, "children": { "UnityEnvironment._generate_step_input": { "total": 297.37677720864303, "count": 1865509, "is_parallel": true, "self": 297.37677720864303 }, "communicator.exchange": { "total": 7506.160344524076, "count": 1865509, "is_parallel": true, "self": 7506.160344524076 }, "steps_from_proto": { "total": 1389.8377382734325, "count": 3731018, "is_parallel": true, "self": 265.6407350411173, "children": { "_process_rank_one_or_two_observation": { "total": 1124.1970032323152, "count": 14924072, "is_parallel": true, "self": 1124.1970032323152 } } } } }, "steps_from_proto": { "total": 0.0874301150906831, "count": 218, "is_parallel": true, "self": 0.017242368310689926, "children": { "_process_rank_one_or_two_observation": { "total": 0.07018774677999318, "count": 872, "is_parallel": true, "self": 0.07018774677999318 } } } } } } } } }, "trainer_advance": { "total": 5107.76952109905, "count": 1865509, "self": 148.80738690984435, "children": { "process_trajectory": { "total": 2398.339024409419, "count": 1865509, "self": 2392.7619246596005, "children": { "RLTrainer._checkpoint": { "total": 5.577099749818444, "count": 54, "self": 5.577099749818444 } } }, "_update_policy": { "total": 2560.6231097797863, "count": 1321, "self": 1509.3422473517712, "children": { "TorchPOCAOptimizer.update": { "total": 1051.280862428015, "count": 39642, "self": 1051.280862428015 } } } } } } }, "trainer_threads": { "total": 5.029141902923584e-07, "count": 1, "self": 5.029141902923584e-07 }, "TrainerController._save_models": { "total": 0.10595928016118705, "count": 1, "self": 0.0008077402599155903, "children": { "RLTrainer._checkpoint": { "total": 0.10515153990127146, "count": 1, "self": 0.10515153990127146 } } } } } } }