{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.128203868865967, "min": 3.128203868865967, "max": 3.2957658767700195, "count": 206 }, "SoccerTwos.Policy.Entropy.sum": { "value": 72374.125, "min": 1788.0172119140625, "max": 136265.984375, "count": 206 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 409.09090909090907, "max": 999.0, "count": 206 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 3996.0, "max": 31704.0, "count": 206 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1187.140805796752, "min": 1186.3808015537347, "max": 1202.2230085734304, "count": 113 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2374.281611593504, "min": 2372.7616031074695, "max": 12019.077019209795, "count": 113 }, "SoccerTwos.Step.mean": { "value": 2059882.0, "min": 9870.0, "max": 2059882.0, "count": 206 }, "SoccerTwos.Step.sum": { "value": 2059882.0, "min": 9870.0, "max": 2059882.0, "count": 206 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0022739688865840435, "min": -0.08057760447263718, "max": 0.01258127298206091, "count": 206 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.02273968979716301, "min": -1.0474029779434204, "max": 0.13839399814605713, "count": 206 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.002308222698047757, "min": -0.08055799454450607, "max": 0.011082419194281101, "count": 206 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.023082226514816284, "min": -1.04714035987854, "max": 0.12190660834312439, "count": 206 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 206 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 206 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.42857142857142855, "max": 0.24627691965836745, "count": 206 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -6.515599966049194, "max": 3.201599955558777, "count": 206 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.42857142857142855, "max": 0.24627691965836745, "count": 206 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -6.515599966049194, "max": 3.201599955558777, "count": 206 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 206 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 206 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017127007464296184, "min": 0.012718712531326067, "max": 0.02266532371577341, "count": 95 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017127007464296184, "min": 0.012718712531326067, "max": 0.02266532371577341, "count": 95 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 2.6337931018360906e-07, "min": 3.0373415900915764e-08, "max": 0.0047818772417182725, "count": 95 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.6337931018360906e-07, "min": 3.0373415900915764e-08, "max": 0.0047818772417182725, "count": 95 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 2.3908658306481814e-07, "min": 4.447467993884402e-08, "max": 0.004926235570261876, "count": 95 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 2.3908658306481814e-07, "min": 4.447467993884402e-08, "max": 0.004926235570261876, "count": 95 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 95 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 95 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 95 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 95 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 95 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 95 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681498125", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:38:11) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/mattsthilaire/miniforge3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos-msthil --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": "1681506612" }, "total": 8486.658130917001, "count": 1, "self": 0.17415554100080044, "children": { "run_training.setup": { "total": 0.0225070839999999, "count": 1, "self": 0.0225070839999999 }, "TrainerController.start_learning": { "total": 8486.461468292, "count": 1, "self": 1.6383473169535137, "children": { "TrainerController._reset_env": { "total": 2.047540998997704, "count": 11, "self": 2.047540998997704 }, "TrainerController.advance": { "total": 8482.65708543405, "count": 135273, "self": 1.5377856332906958, "children": { "env_step": { "total": 7091.909376126942, "count": 135273, "self": 6852.133794364885, "children": { "SubprocessEnvManager._take_step": { "total": 238.60045398310086, "count": 135273, "self": 7.588517586055616, "children": { "TorchPolicy.evaluate": { "total": 231.01193639704525, "count": 268664, "self": 231.01193639704525 } } }, "workers": { "total": 1.175127778956595, "count": 135272, "self": 0.0, "children": { "worker_root": { "total": 8482.058684237982, "count": 135272, "is_parallel": true, "self": 1874.931821495833, "children": { "steps_from_proto": { "total": 0.018282249998494038, "count": 22, "is_parallel": true, "self": 0.0021257099963478687, "children": { "_process_rank_one_or_two_observation": { "total": 0.01615654000214617, "count": 88, "is_parallel": true, "self": 0.01615654000214617 } } }, "UnityEnvironment.step": { "total": 6607.10858049215, "count": 135272, "is_parallel": true, "self": 16.547839282236964, "children": { "UnityEnvironment._generate_step_input": { "total": 114.60310194199081, "count": 135272, "is_parallel": true, "self": 114.60310194199081 }, "communicator.exchange": { "total": 6235.002833573965, "count": 135272, "is_parallel": true, "self": 6235.002833573965 }, "steps_from_proto": { "total": 240.95480569395727, "count": 270544, "is_parallel": true, "self": 26.317884138651635, "children": { "_process_rank_one_or_two_observation": { "total": 214.63692155530563, "count": 1082176, "is_parallel": true, "self": 214.63692155530563 } } } } } } } } } } }, "trainer_advance": { "total": 1389.2099236738163, "count": 135272, "self": 13.43716021274804, "children": { "process_trajectory": { "total": 209.26003329406998, "count": 135272, "self": 208.83696458606923, "children": { "RLTrainer._checkpoint": { "total": 0.4230687080007556, "count": 4, "self": 0.4230687080007556 } } }, "_update_policy": { "total": 1166.5127301669984, "count": 95, "self": 177.76332381099155, "children": { "TorchPOCAOptimizer.update": { "total": 988.7494063560068, "count": 2859, "self": 988.7494063560068 } } } } } } }, "trainer_threads": { "total": 6.249993020901456e-07, "count": 1, "self": 6.249993020901456e-07 }, "TrainerController._save_models": { "total": 0.11849391699979606, "count": 1, "self": 0.0015337090007960796, "children": { "RLTrainer._checkpoint": { "total": 0.11696020799899998, "count": 1, "self": 0.11696020799899998 } } } } } } }