{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0051374435424805, "min": 1.9756574630737305, "max": 3.2957327365875244, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38883.625, "min": 22461.34375, "max": 112020.296875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.11827956989247, "min": 45.49074074074074, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19016.0, "min": 15856.0, "max": 26652.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1596.6838735471788, "min": 1198.122229794541, "max": 1611.2718930898798, "count": 482 }, "SoccerTwos.Self-play.ELO.sum": { "value": 296983.20047977526, "min": 2396.244459589082, "max": 347297.2762489767, "count": 482 }, "SoccerTwos.Step.mean": { "value": 4999995.0, "min": 9342.0, "max": 4999995.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999995.0, "min": 9342.0, "max": 4999995.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.006804786156862974, "min": -0.1280451864004135, "max": 0.18309754133224487, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.2724950313568115, "min": -15.237281799316406, "max": 22.887191772460938, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.012299755588173866, "min": -0.12442772835493088, "max": 0.18262533843517303, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.3000543117523193, "min": -14.837784767150879, "max": 22.828166961669922, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.03338288814626276, "min": -0.5124909092079509, "max": 0.523600003936074, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.242600083351135, "min": -43.53259986639023, "max": 53.52099972963333, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.03338288814626276, "min": -0.5124909092079509, "max": 0.523600003936074, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.242600083351135, "min": -43.53259986639023, "max": 53.52099972963333, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016495755713549443, "min": 0.01132660136014844, "max": 0.024602351003947358, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016495755713549443, "min": 0.01132660136014844, "max": 0.024602351003947358, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11248422265052796, "min": 1.2023195968898412e-06, "max": 0.1173616699874401, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11248422265052796, "min": 1.2023195968898412e-06, "max": 0.1173616699874401, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11500127116839091, "min": 1.4417202616338424e-06, "max": 0.12001050611337026, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11500127116839091, "min": 1.4417202616338424e-06, "max": 0.12001050611337026, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680505034", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/mnt/slurm-home/h_kambe/miniconda3/envs/py39-deep-rl-class/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.2+cu111", "numpy_version": "1.21.2", "end_time_seconds": "1680510224" }, "total": 5189.2261346541345, "count": 1, "self": 0.2708319826051593, "children": { "run_training.setup": { "total": 0.057166741229593754, "count": 1, "self": 0.057166741229593754 }, "TrainerController.start_learning": { "total": 5188.8981359303, "count": 1, "self": 4.812366155907512, "children": { "TrainerController._reset_env": { "total": 4.374634736217558, "count": 25, "self": 4.374634736217558 }, "TrainerController.advance": { "total": 5179.4017368573695, "count": 337963, "self": 4.786904287524521, "children": { "env_step": { "total": 3820.0134374303743, "count": 337963, "self": 2759.8225334323943, "children": { "SubprocessEnvManager._take_step": { "total": 1057.3603545734659, "count": 337963, "self": 27.27372412662953, "children": { "TorchPolicy.evaluate": { "total": 1030.0866304468364, "count": 632118, "self": 1030.0866304468364 } } }, "workers": { "total": 2.8305494245141745, "count": 337963, "self": 0.0, "children": { "worker_root": { "total": 5182.174006629735, "count": 337963, "is_parallel": true, "self": 2961.3144504204392, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015860162675380707, "count": 2, "is_parallel": true, "self": 0.00037961360067129135, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012064026668667793, "count": 8, "is_parallel": true, "self": 0.0012064026668667793 } } }, "UnityEnvironment.step": { "total": 0.016123839654028416, "count": 1, "is_parallel": true, "self": 0.00039878953248262405, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031753815710544586, "count": 1, "is_parallel": true, "self": 0.00031753815710544586 }, "communicator.exchange": { "total": 0.014197691343724728, "count": 1, "is_parallel": true, "self": 0.014197691343724728 }, "steps_from_proto": { "total": 0.0012098206207156181, "count": 2, "is_parallel": true, "self": 0.00026405882090330124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009457617998123169, "count": 8, "is_parallel": true, "self": 0.0009457617998123169 } } } } } } }, "UnityEnvironment.step": { "total": 2220.8298132624477, "count": 337962, "is_parallel": true, "self": 119.70537663344294, "children": { "UnityEnvironment._generate_step_input": { "total": 87.01921977289021, "count": 337962, "is_parallel": true, "self": 87.01921977289021 }, "communicator.exchange": { "total": 1630.5717726554722, "count": 337962, "is_parallel": true, "self": 1630.5717726554722 }, "steps_from_proto": { "total": 383.5334442006424, "count": 675924, "is_parallel": true, "self": 82.07232023123652, "children": { "_process_rank_one_or_two_observation": { "total": 301.4611239694059, "count": 2703696, "is_parallel": true, "self": 301.4611239694059 } } } } }, "steps_from_proto": { "total": 0.029742946848273277, "count": 48, "is_parallel": true, "self": 0.006534799002110958, "children": { "_process_rank_one_or_two_observation": { "total": 0.02320814784616232, "count": 192, "is_parallel": true, "self": 0.02320814784616232 } } } } } } } } }, "trainer_advance": { "total": 1354.6013951394707, "count": 337963, "self": 33.399527471512556, "children": { "process_trajectory": { "total": 551.6175352819264, "count": 337963, "self": 548.4771730527282, "children": { "RLTrainer._checkpoint": { "total": 3.1403622291982174, "count": 10, "self": 3.1403622291982174 } } }, "_update_policy": { "total": 769.5843323860317, "count": 240, "self": 523.5356768295169, "children": { "TorchPOCAOptimizer.update": { "total": 246.04865555651486, "count": 7203, "self": 246.04865555651486 } } } } } } }, "trainer_threads": { "total": 6.472691893577576e-07, "count": 1, "self": 6.472691893577576e-07 }, "TrainerController._save_models": { "total": 0.30939753353595734, "count": 1, "self": 0.00950619112700224, "children": { "RLTrainer._checkpoint": { "total": 0.2998913424089551, "count": 1, "self": 0.2998913424089551 } } } } } } }