{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1853554248809814, "min": 3.165717601776123, "max": 3.256704092025757, "count": 90 }, "SoccerTwos.Policy.Entropy.sum": { "value": 59120.1953125, "min": 22107.51953125, "max": 104214.53125, "count": 90 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 836.5, "min": 426.27272727272725, "max": 999.0, "count": 90 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20076.0, "min": 13232.0, "max": 26708.0, "count": 90 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1183.3640282982788, "min": 1181.9704321645243, "max": 1200.795990516056, "count": 75 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2366.7280565965575, "min": 2363.9408643290485, "max": 11929.302938331019, "count": 75 }, "SoccerTwos.Step.mean": { "value": 999948.0, "min": 109698.0, "max": 999948.0, "count": 90 }, "SoccerTwos.Step.sum": { "value": 999948.0, "min": 109698.0, "max": 999948.0, "count": 90 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007164405658841133, "min": -0.014982464723289013, "max": 0.029016362503170967, "count": 90 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.0859728679060936, "min": -0.15068447589874268, "max": 0.42887791991233826, "count": 90 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.007166388910263777, "min": -0.01595994271337986, "max": 0.029594743624329567, "count": 90 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.08599666506052017, "min": -0.19151932001113892, "max": 0.4353296160697937, "count": 90 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 90 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 90 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.16666666666666666, "min": -0.5833333333333334, "max": 0.32618666092554727, "count": 90 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -7.710799992084503, "max": 4.892799913883209, "count": 90 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.16666666666666666, "min": -0.5833333333333334, "max": 0.32618666092554727, "count": 90 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -7.710799992084503, "max": 4.892799913883209, "count": 90 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 90 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 90 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017051780303396904, "min": 0.010264106953400187, "max": 0.021436606487259268, "count": 41 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017051780303396904, "min": 0.010264106953400187, "max": 0.021436606487259268, "count": 41 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.00041840440680971367, "min": 7.760814499609599e-06, "max": 0.004851551392736534, "count": 41 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.00041840440680971367, "min": 7.760814499609599e-06, "max": 0.004851551392736534, "count": 41 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.000418744977893463, "min": 8.187464648775252e-06, "max": 0.005020396752903859, "count": 41 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.000418744977893463, "min": 8.187464648775252e-06, "max": 0.005020396752903859, "count": 41 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 41 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 41 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 41 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 41 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 41 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 41 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689262993", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "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": "1689265045" }, "total": 2051.8194522780004, "count": 1, "self": 0.38692356800038397, "children": { "run_training.setup": { "total": 0.04912061800041556, "count": 1, "self": 0.04912061800041556 }, "TrainerController.start_learning": { "total": 2051.3834080919996, "count": 1, "self": 1.4297072327517526, "children": { "TrainerController._reset_env": { "total": 5.8505743470004745, "count": 5, "self": 5.8505743470004745 }, "TrainerController.advance": { "total": 2043.8246442432464, "count": 58741, "self": 1.5466441024855158, "children": { "env_step": { "total": 1650.7772208318975, "count": 58741, "self": 1301.426601842818, "children": { "SubprocessEnvManager._take_step": { "total": 348.49107166401063, "count": 58741, "self": 10.864575685266573, "children": { "TorchPolicy.evaluate": { "total": 337.62649597874406, "count": 116608, "self": 337.62649597874406 } } }, "workers": { "total": 0.8595473250688883, "count": 58741, "self": 0.0, "children": { "worker_root": { "total": 2047.0026537257418, "count": 58741, "is_parallel": true, "self": 944.84341135869, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00418624399935652, "count": 2, "is_parallel": true, "self": 0.0009510939989922917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032351500003642286, "count": 8, "is_parallel": true, "self": 0.0032351500003642286 } } }, "UnityEnvironment.step": { "total": 0.08429741999952967, "count": 1, "is_parallel": true, "self": 0.00380554699950153, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009018929995363578, "count": 1, "is_parallel": true, "self": 0.0009018929995363578 }, "communicator.exchange": { "total": 0.07381326599988824, "count": 1, "is_parallel": true, "self": 0.07381326599988824 }, "steps_from_proto": { "total": 0.005776714000603533, "count": 2, "is_parallel": true, "self": 0.0015629140034434386, "children": { "_process_rank_one_or_two_observation": { "total": 0.004213799997160095, "count": 8, "is_parallel": true, "self": 0.004213799997160095 } } } } } } }, "UnityEnvironment.step": { "total": 1102.1488647630513, "count": 58740, "is_parallel": true, "self": 64.87031498196848, "children": { "UnityEnvironment._generate_step_input": { "total": 42.68622125575712, "count": 58740, "is_parallel": true, "self": 42.68622125575712 }, "communicator.exchange": { "total": 776.845947855023, "count": 58740, "is_parallel": true, "self": 776.845947855023 }, "steps_from_proto": { "total": 217.74638067030264, "count": 117480, "is_parallel": true, "self": 35.14515632017719, "children": { "_process_rank_one_or_two_observation": { "total": 182.60122435012545, "count": 469920, "is_parallel": true, "self": 182.60122435012545 } } } } }, "steps_from_proto": { "total": 0.010377604000495921, "count": 8, "is_parallel": true, "self": 0.001878691000456456, "children": { "_process_rank_one_or_two_observation": { "total": 0.008498913000039465, "count": 32, "is_parallel": true, "self": 0.008498913000039465 } } } } } } } } }, "trainer_advance": { "total": 391.50077930886346, "count": 58741, "self": 13.187245363963484, "children": { "process_trajectory": { "total": 99.65893102790506, "count": 58741, "self": 98.97506984290521, "children": { "RLTrainer._checkpoint": { "total": 0.6838611849998415, "count": 2, "self": 0.6838611849998415 } } }, "_update_policy": { "total": 278.6546029169949, "count": 41, "self": 176.7638483069668, "children": { "TorchPOCAOptimizer.update": { "total": 101.89075461002813, "count": 1230, "self": 101.89075461002813 } } } } } } }, "trainer_threads": { "total": 9.930008673109114e-07, "count": 1, "self": 9.930008673109114e-07 }, "TrainerController._save_models": { "total": 0.2784812760000932, "count": 1, "self": 0.002167464999729418, "children": { "RLTrainer._checkpoint": { "total": 0.2763138110003638, "count": 1, "self": 0.2763138110003638 } } } } } } }