{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.9653992652893066, "min": 2.928091049194336, "max": 3.089735984802246, "count": 75 }, "SoccerTwos.Policy.Entropy.sum": { "value": 55322.48828125, "min": 30992.189453125, "max": 94720.8671875, "count": 75 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 258.5263157894737, "min": 126.6923076923077, "max": 539.2222222222222, "count": 75 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19648.0, "min": 16400.0, "max": 23072.0, "count": 75 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1288.917142349652, "min": 1265.364925775114, "max": 1319.9948589635467, "count": 75 }, "SoccerTwos.Self-play.ELO.sum": { "value": 46401.01712458747, "min": 17796.887486172378, "max": 99141.74676083495, "count": 75 }, "SoccerTwos.Step.mean": { "value": 4249607.0, "min": 3509874.0, "max": 4249607.0, "count": 75 }, "SoccerTwos.Step.sum": { "value": 4249607.0, "min": 3509874.0, "max": 4249607.0, "count": 75 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.033912427723407745, "min": -0.02116245962679386, "max": 0.08301462978124619, "count": 75 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.322584629058838, "min": -1.5871844291687012, "max": 4.439652919769287, "count": 75 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.035285141319036484, "min": -0.031118163838982582, "max": 0.0905672013759613, "count": 75 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.3761205673217773, "min": -2.3338623046875, "max": 5.524599075317383, "count": 75 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 75 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 75 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.03541025595787244, "min": -0.5060222225470675, "max": 0.3610142873866217, "count": 75 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.3809999823570251, "min": -19.56760013103485, "max": 17.24120005965233, "count": 75 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.03541025595787244, "min": -0.5060222225470675, "max": 0.3610142873866217, "count": 75 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.3809999823570251, "min": -19.56760013103485, "max": 17.24120005965233, "count": 75 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 75 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 75 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016938292739602425, "min": 0.010926229831723807, "max": 0.02053702191139261, "count": 35 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016938292739602425, "min": 0.010926229831723807, "max": 0.02053702191139261, "count": 35 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.026586440950632097, "min": 0.012621084662775199, "max": 0.03861811061700185, "count": 35 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.026586440950632097, "min": 0.012621084662775199, "max": 0.03861811061700185, "count": 35 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.027341894370814166, "min": 0.012977093706528347, "max": 0.03994991021851699, "count": 35 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.027341894370814166, "min": 0.012977093706528347, "max": 0.03994991021851699, "count": 35 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 35 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 35 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 35 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 35 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 35 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 35 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690878657", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu", "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": "1690881716" }, "total": 3059.7732766870004, "count": 1, "self": 1.0997174930007532, "children": { "run_training.setup": { "total": 0.04625938999970458, "count": 1, "self": 0.04625938999970458 }, "TrainerController.start_learning": { "total": 3058.627299804, "count": 1, "self": 1.995636533916695, "children": { "TrainerController._reset_env": { "total": 1.7464096760004395, "count": 5, "self": 1.7464096760004395 }, "TrainerController.advance": { "total": 3054.504729847082, "count": 49247, "self": 2.1494134940912772, "children": { "env_step": { "total": 1728.580282753981, "count": 49247, "self": 1451.0359896730588, "children": { "SubprocessEnvManager._take_step": { "total": 276.30703805185794, "count": 49247, "self": 14.137087277108094, "children": { "TorchPolicy.evaluate": { "total": 262.16995077474985, "count": 95670, "self": 262.16995077474985 } } }, "workers": { "total": 1.237255029064272, "count": 49247, "self": 0.0, "children": { "worker_root": { "total": 3040.5957244619613, "count": 49247, "is_parallel": true, "self": 1839.4196168309827, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004600864000167348, "count": 2, "is_parallel": true, "self": 0.0013356340009522683, "children": { "_process_rank_one_or_two_observation": { "total": 0.00326522999921508, "count": 8, "is_parallel": true, "self": 0.00326522999921508 } } }, "UnityEnvironment.step": { "total": 0.05661161500029266, "count": 1, "is_parallel": true, "self": 0.0014208450006663043, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0015787909997015959, "count": 1, "is_parallel": true, "self": 0.0015787909997015959 }, "communicator.exchange": { "total": 0.04902488400011862, "count": 1, "is_parallel": true, "self": 0.04902488400011862 }, "steps_from_proto": { "total": 0.0045870949998061405, "count": 2, "is_parallel": true, "self": 0.0008254869999291259, "children": { "_process_rank_one_or_two_observation": { "total": 0.0037616079998770147, "count": 8, "is_parallel": true, "self": 0.0037616079998770147 } } } } } } }, "steps_from_proto": { "total": 0.012616636001439474, "count": 8, "is_parallel": true, "self": 0.0025250890007555427, "children": { "_process_rank_one_or_two_observation": { "total": 0.010091547000683931, "count": 32, "is_parallel": true, "self": 0.010091547000683931 } } }, "UnityEnvironment.step": { "total": 1201.163490994977, "count": 49246, "is_parallel": true, "self": 71.97562404471091, "children": { "UnityEnvironment._generate_step_input": { "total": 37.76953575507514, "count": 49246, "is_parallel": true, "self": 37.76953575507514 }, "communicator.exchange": { "total": 862.6202264811259, "count": 49246, "is_parallel": true, "self": 862.6202264811259 }, "steps_from_proto": { "total": 228.79810471406518, "count": 98492, "is_parallel": true, "self": 41.2123752680468, "children": { "_process_rank_one_or_two_observation": { "total": 187.58572944601838, "count": 393968, "is_parallel": true, "self": 187.58572944601838 } } } } } } } } } } }, "trainer_advance": { "total": 1323.77503359901, "count": 49247, "self": 16.65251782910582, "children": { "process_trajectory": { "total": 211.0241680079057, "count": 49247, "self": 210.79081530890608, "children": { "RLTrainer._checkpoint": { "total": 0.2333526989996244, "count": 1, "self": 0.2333526989996244 } } }, "_update_policy": { "total": 1096.0983477619984, "count": 35, "self": 203.32014813700744, "children": { "TorchPOCAOptimizer.update": { "total": 892.778199624991, "count": 1050, "self": 892.778199624991 } } } } } } }, "trainer_threads": { "total": 2.0180004867142998e-06, "count": 1, "self": 2.0180004867142998e-06 }, "TrainerController._save_models": { "total": 0.38052172900006553, "count": 1, "self": 0.0025554750000083004, "children": { "RLTrainer._checkpoint": { "total": 0.37796625400005723, "count": 1, "self": 0.37796625400005723 } } } } } } }