{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6175289154052734, "min": 1.6175289154052734, "max": 1.6452361345291138, "count": 7 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31004.794921875, "min": 1367.9613037109375, "max": 34486.40234375, "count": 7 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 68.4931506849315, "min": 11.5, "max": 68.4931506849315, "count": 7 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20000.0, "min": 92.0, "max": 20000.0, "count": 7 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1199.6589662120994, "min": 1194.7646503162598, "max": 1205.486328943782, "count": 7 }, "SoccerTwos.Self-play.ELO.sum": { "value": 175150.2090669665, "min": 4800.0, "max": 199670.16142830084, "count": 7 }, "SoccerTwos.Step.mean": { "value": 15059982.0, "min": 14999985.0, "max": 15059982.0, "count": 7 }, "SoccerTwos.Step.sum": { "value": 15059982.0, "min": 14999985.0, "max": 15059982.0, "count": 7 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.08485712110996246, "min": -0.21045248210430145, "max": -0.0027830300386995077, "count": 7 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -12.389139175415039, "min": -12.389139175415039, "max": -0.41188845038414, "count": 7 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08918455988168716, "min": -0.20541344583034515, "max": -0.006354253739118576, "count": 7 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -13.02094554901123, "min": -13.02094554901123, "max": -0.6162403225898743, "count": 7 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 7 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 7 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2063452078871531, "min": -1.0, "max": 0.12662162249152725, "count": 7 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -30.126400351524353, "min": -30.126400351524353, "max": 18.740000128746033, "count": 7 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2063452078871531, "min": -1.0, "max": 0.12662162249152725, "count": 7 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -30.126400351524353, "min": -30.126400351524353, "max": 18.740000128746033, "count": 7 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.021047038274506727, "min": 0.014849630450286592, "max": 0.021047038274506727, "count": 2 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.021047038274506727, "min": 0.014849630450286592, "max": 0.021047038274506727, "count": 2 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09795060604810715, "min": 0.09790906980633736, "max": 0.09795060604810715, "count": 2 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09795060604810715, "min": 0.09790906980633736, "max": 0.09795060604810715, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10036184812585512, "min": 0.09985422864556312, "max": 0.10036184812585512, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10036184812585512, "min": 0.09985422864556312, "max": 0.10036184812585512, "count": 2 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680763245", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\ProgramData\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos3 --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1680763411" }, "total": 166.05881739999998, "count": 1, "self": 0.00738530000000992, "children": { "run_training.setup": { "total": 0.10945179999999999, "count": 1, "self": 0.10945179999999999 }, "TrainerController.start_learning": { "total": 165.94198029999998, "count": 1, "self": 0.10049440000025811, "children": { "TrainerController._reset_env": { "total": 4.1218941000000004, "count": 2, "self": 4.1218941000000004 }, "TrainerController.advance": { "total": 161.60429159999973, "count": 4293, "self": 0.0802258999985952, "children": { "env_step": { "total": 57.23557130000063, "count": 4293, "self": 44.29359930000111, "children": { "SubprocessEnvManager._take_step": { "total": 12.885823999999628, "count": 4293, "self": 0.5079915000002213, "children": { "TorchPolicy.evaluate": { "total": 12.377832499999407, "count": 7804, "self": 12.377832499999407 } } }, "workers": { "total": 0.056147999999890175, "count": 4293, "self": 0.0, "children": { "worker_root": { "total": 140.4687641999996, "count": 4293, "is_parallel": true, "self": 105.82835569999918, "children": { "steps_from_proto": { "total": 0.003049300000001587, "count": 4, "is_parallel": true, "self": 0.000592000000000148, "children": { "_process_rank_one_or_two_observation": { "total": 0.002457300000001439, "count": 16, "is_parallel": true, "self": 0.002457300000001439 } } }, "UnityEnvironment.step": { "total": 34.63735920000043, "count": 4293, "is_parallel": true, "self": 1.947230000000033, "children": { "UnityEnvironment._generate_step_input": { "total": 1.639454400000341, "count": 4293, "is_parallel": true, "self": 1.639454400000341 }, "communicator.exchange": { "total": 25.24228060000031, "count": 4293, "is_parallel": true, "self": 25.24228060000031 }, "steps_from_proto": { "total": 5.808394199999744, "count": 8586, "is_parallel": true, "self": 1.1771927000000417, "children": { "_process_rank_one_or_two_observation": { "total": 4.631201499999702, "count": 34344, "is_parallel": true, "self": 4.631201499999702 } } } } } } } } } } }, "trainer_advance": { "total": 104.28849440000052, "count": 4293, "self": 0.7541314000011425, "children": { "process_trajectory": { "total": 17.68527299999938, "count": 4293, "self": 17.53359369999938, "children": { "RLTrainer._checkpoint": { "total": 0.15167930000000052, "count": 1, "self": 0.15167930000000052 } } }, "_update_policy": { "total": 85.84908999999999, "count": 3, "self": 7.088042699999946, "children": { "TorchPOCAOptimizer.update": { "total": 78.76104730000004, "count": 80, "self": 78.76104730000004 } } } } } } }, "trainer_threads": { "total": 1.3000000080864993e-06, "count": 1, "self": 1.3000000080864993e-06 }, "TrainerController._save_models": { "total": 0.1152988999999991, "count": 1, "self": 0.003764600000010887, "children": { "RLTrainer._checkpoint": { "total": 0.1115342999999882, "count": 1, "self": 0.1115342999999882 } } } } } } }