{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.7906553745269775, "min": 2.7906553745269775, "max": 3.152825355529785, "count": 101 }, "SoccerTwos.Policy.Entropy.sum": { "value": 52776.875, "min": 24525.296875, "max": 97737.3125, "count": 101 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 67.34246575342466, "min": 67.34246575342466, "max": 999.0, "count": 101 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19664.0, "min": 1996.0, "max": 25168.0, "count": 101 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1368.9925788732346, "min": 1197.771800761118, "max": 1374.9423377357964, "count": 100 }, "SoccerTwos.Self-play.ELO.sum": { "value": 199872.91651549225, "min": 2399.287847992216, "max": 199872.91651549225, "count": 100 }, "SoccerTwos.Step.mean": { "value": 2499997.0, "min": 1499670.0, "max": 2499997.0, "count": 101 }, "SoccerTwos.Step.sum": { "value": 2499997.0, "min": 1499670.0, "max": 2499997.0, "count": 101 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.07111520320177078, "min": -0.011479731649160385, "max": 0.18219316005706787, "count": 101 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 10.382819175720215, "min": -0.1940249353647232, "max": 19.814180374145508, "count": 101 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0729760229587555, "min": -0.011654743924736977, "max": 0.19274993240833282, "count": 101 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 10.654499053955078, "min": -0.19143153727054596, "max": 19.98401641845703, "count": 101 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 101 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 101 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.08395068286216423, "min": -0.46153846153846156, "max": 0.8119999965031942, "count": 101 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 12.256799697875977, "min": -19.759999990463257, "max": 56.10360026359558, "count": 101 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.08395068286216423, "min": -0.46153846153846156, "max": 0.8119999965031942, "count": 101 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 12.256799697875977, "min": -19.759999990463257, "max": 56.10360026359558, "count": 101 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 101 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 101 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015483492726343685, "min": 0.012218045504050678, "max": 0.020981896084655696, "count": 47 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015483492726343685, "min": 0.012218045504050678, "max": 0.020981896084655696, "count": 47 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.06869931096831958, "min": 0.0008851464566153785, "max": 0.07153118501106898, "count": 47 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.06869931096831958, "min": 0.0008851464566153785, "max": 0.07153118501106898, "count": 47 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07002369984984398, "min": 0.0008841153399165099, "max": 0.07281648889183998, "count": 47 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07002369984984398, "min": 0.0008841153399165099, "max": 0.07281648889183998, "count": 47 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 47 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 47 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 47 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 47 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 47 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 47 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682565264", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/aditya/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "1682567120" }, "total": 1855.288408743, "count": 1, "self": 0.14905989399971986, "children": { "run_training.setup": { "total": 0.01727315800002316, "count": 1, "self": 0.01727315800002316 }, "TrainerController.start_learning": { "total": 1855.1220756910002, "count": 1, "self": 1.1945324059847735, "children": { "TrainerController._reset_env": { "total": 3.7868088770001975, "count": 7, "self": 3.7868088770001975 }, "TrainerController.advance": { "total": 1849.904136448015, "count": 65883, "self": 1.147340069051097, "children": { "env_step": { "total": 1493.1885693970078, "count": 65883, "self": 1253.6573550250293, "children": { "SubprocessEnvManager._take_step": { "total": 238.74028168898235, "count": 65883, "self": 9.542910278967582, "children": { "TorchPolicy.evaluate": { "total": 229.19737141001477, "count": 128284, "self": 229.19737141001477 } } }, "workers": { "total": 0.7909326829961572, "count": 65882, "self": 0.0, "children": { "worker_root": { "total": 1852.103163405006, "count": 65882, "is_parallel": true, "self": 767.2810382349901, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004625854999972034, "count": 2, "is_parallel": true, "self": 0.0011449340000240227, "children": { "_process_rank_one_or_two_observation": { "total": 0.0034809209999480117, "count": 8, "is_parallel": true, "self": 0.0034809209999480117 } } }, "UnityEnvironment.step": { "total": 0.032590048999992405, "count": 1, "is_parallel": true, "self": 0.001097213999997848, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0011243229999990945, "count": 1, "is_parallel": true, "self": 0.0011243229999990945 }, "communicator.exchange": { "total": 0.02731038499999272, "count": 1, "is_parallel": true, "self": 0.02731038499999272 }, "steps_from_proto": { "total": 0.0030581270000027416, "count": 2, "is_parallel": true, "self": 0.0005138349999924685, "children": { "_process_rank_one_or_two_observation": { "total": 0.002544292000010273, "count": 8, "is_parallel": true, "self": 0.002544292000010273 } } } } } } }, "steps_from_proto": { "total": 0.017299582000248392, "count": 12, "is_parallel": true, "self": 0.0027732200001935325, "children": { "_process_rank_one_or_two_observation": { "total": 0.01452636200005486, "count": 48, "is_parallel": true, "self": 0.01452636200005486 } } }, "UnityEnvironment.step": { "total": 1084.8048255880155, "count": 65881, "is_parallel": true, "self": 70.96715294294768, "children": { "UnityEnvironment._generate_step_input": { "total": 50.272730726058654, "count": 65881, "is_parallel": true, "self": 50.272730726058654 }, "communicator.exchange": { "total": 769.0471808799995, "count": 65881, "is_parallel": true, "self": 769.0471808799995 }, "steps_from_proto": { "total": 194.51776103900983, "count": 131762, "is_parallel": true, "self": 31.265090789089328, "children": { "_process_rank_one_or_two_observation": { "total": 163.2526702499205, "count": 527048, "is_parallel": true, "self": 163.2526702499205 } } } } } } } } } } }, "trainer_advance": { "total": 355.5682269819562, "count": 65882, "self": 9.973383588958313, "children": { "process_trajectory": { "total": 86.49029842099756, "count": 65882, "self": 85.90375237299739, "children": { "RLTrainer._checkpoint": { "total": 0.586546048000173, "count": 3, "self": 0.586546048000173 } } }, "_update_policy": { "total": 259.1045449720003, "count": 47, "self": 132.59572539199553, "children": { "TorchPOCAOptimizer.update": { "total": 126.5088195800048, "count": 1410, "self": 126.5088195800048 } } } } } } }, "trainer_threads": { "total": 6.51000391371781e-07, "count": 1, "self": 6.51000391371781e-07 }, "TrainerController._save_models": { "total": 0.23659730899998976, "count": 1, "self": 0.0022121010001683317, "children": { "RLTrainer._checkpoint": { "total": 0.23438520799982143, "count": 1, "self": 0.23438520799982143 } } } } } } }