{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.361954927444458, "min": 1.262857437133789, "max": 3.2957355976104736, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 25757.291015625, "min": 15620.099609375, "max": 117655.28125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.756410256410255, "min": 40.48360655737705, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19580.0, "min": 14648.0, "max": 27152.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1559.9802077639051, "min": 1184.7323955041884, "max": 1646.3269700740036, "count": 4996 }, "SoccerTwos.Self-play.ELO.sum": { "value": 243356.9124111692, "min": 2373.392667291438, "max": 375835.9142462027, "count": 4996 }, "SoccerTwos.Step.mean": { "value": 49999954.0, "min": 9594.0, "max": 49999954.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999954.0, "min": 9594.0, "max": 49999954.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.014303267002105713, "min": -0.13483084738254547, "max": 0.1903652846813202, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.231309652328491, "min": -24.19184112548828, "max": 34.07538604736328, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01100306585431099, "min": -0.13653536140918732, "max": 0.18597352504730225, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.7164782285690308, "min": -24.32894515991211, "max": 33.28926086425781, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07812051054758903, "min": -0.6948631570527428, "max": 0.4290448994863601, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 12.18679964542389, "min": -69.70360004901886, "max": 72.96079981327057, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07812051054758903, "min": -0.6948631570527428, "max": 0.4290448994863601, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 12.18679964542389, "min": -69.70360004901886, "max": 72.96079981327057, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019285838552968927, "min": 0.010190736107809547, "max": 0.026264598076037753, "count": 2425 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019285838552968927, "min": 0.010190736107809547, "max": 0.026264598076037753, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1092404951651891, "min": 2.454656720753216e-05, "max": 0.12859602173169454, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1092404951651891, "min": 2.454656720753216e-05, "max": 0.12859602173169454, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11032640139261882, "min": 2.5949599451754086e-05, "max": 0.13178482204675673, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11032640139261882, "min": 2.5949599451754086e-05, "max": 0.13178482204675673, "count": 2425 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2425 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2425 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689614133", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/vincent/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1689743618" }, "total": 129485.55653460699, "count": 1, "self": 1.1277170519897481, "children": { "run_training.setup": { "total": 0.061667037999995955, "count": 1, "self": 0.061667037999995955 }, "TrainerController.start_learning": { "total": 129484.367150517, "count": 1, "self": 70.88670170893602, "children": { "TrainerController._reset_env": { "total": 14.45478453100452, "count": 250, "self": 14.45478453100452 }, "TrainerController.advance": { "total": 129398.37158261807, "count": 3457793, "self": 63.030884157138644, "children": { "env_step": { "total": 103442.38275781812, "count": 3457793, "self": 66855.73324413743, "children": { "SubprocessEnvManager._take_step": { "total": 36544.75495399686, "count": 3457793, "self": 392.64233939121914, "children": { "TorchPolicy.evaluate": { "total": 36152.11261460564, "count": 6277508, "self": 36152.11261460564 } } }, "workers": { "total": 41.89455968383368, "count": 3457793, "self": 0.0, "children": { "worker_root": { "total": 129334.89814316136, "count": 3457793, "is_parallel": true, "self": 69837.27106570205, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023529780000899336, "count": 2, "is_parallel": true, "self": 0.0007397080001965151, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016132699998934186, "count": 8, "is_parallel": true, "self": 0.0016132699998934186 } } }, "UnityEnvironment.step": { "total": 0.04999784599999657, "count": 1, "is_parallel": true, "self": 0.000550720999854093, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039087200002541067, "count": 1, "is_parallel": true, "self": 0.00039087200002541067 }, "communicator.exchange": { "total": 0.0474924430000101, "count": 1, "is_parallel": true, "self": 0.0474924430000101 }, "steps_from_proto": { "total": 0.0015638100001069688, "count": 2, "is_parallel": true, "self": 0.0002691550000690768, "children": { "_process_rank_one_or_two_observation": { "total": 0.001294655000037892, "count": 8, "is_parallel": true, "self": 0.001294655000037892 } } } } } } }, "UnityEnvironment.step": { "total": 59497.23590033541, "count": 3457792, "is_parallel": true, "self": 1828.7969931862608, "children": { "UnityEnvironment._generate_step_input": { "total": 1151.8733344870716, "count": 3457792, "is_parallel": true, "self": 1151.8733344870716 }, "communicator.exchange": { "total": 51425.420356478324, "count": 3457792, "is_parallel": true, "self": 51425.420356478324 }, "steps_from_proto": { "total": 5091.145216183748, "count": 6915584, "is_parallel": true, "self": 873.5513965221808, "children": { "_process_rank_one_or_two_observation": { "total": 4217.593819661567, "count": 27662336, "is_parallel": true, "self": 4217.593819661567 } } } } }, "steps_from_proto": { "total": 0.3911771239074824, "count": 498, "is_parallel": true, "self": 0.06634815023471674, "children": { "_process_rank_one_or_two_observation": { "total": 0.32482897367276564, "count": 1992, "is_parallel": true, "self": 0.32482897367276564 } } } } } } } } }, "trainer_advance": { "total": 25892.957940642817, "count": 3457793, "self": 508.9712585134257, "children": { "process_trajectory": { "total": 14946.23177900286, "count": 3457793, "self": 14889.522046351844, "children": { "RLTrainer._checkpoint": { "total": 56.70973265101611, "count": 100, "self": 56.70973265101611 } } }, "_update_policy": { "total": 10437.754903126533, "count": 2425, "self": 6343.293706739607, "children": { "TorchPOCAOptimizer.update": { "total": 4094.461196386927, "count": 72753, "self": 4094.461196386927 } } } } } } }, "trainer_threads": { "total": 5.610054358839989e-07, "count": 1, "self": 5.610054358839989e-07 }, "TrainerController._save_models": { "total": 0.6540810979931848, "count": 1, "self": 0.03129040700150654, "children": { "RLTrainer._checkpoint": { "total": 0.6227906909916783, "count": 1, "self": 0.6227906909916783 } } } } } } }