{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.796678066253662, "min": 1.6508715152740479, "max": 3.2956461906433105, "count": 639 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35818.57421875, "min": 30144.603515625, "max": 113694.0, "count": 639 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.654761904761905, "min": 37.40769230769231, "max": 999.0, "count": 639 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19708.0, "min": 16716.0, "max": 23924.0, "count": 639 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1455.7522662230756, "min": 1185.6997976068483, "max": 1503.2913772759614, "count": 631 }, "SoccerTwos.Self-play.ELO.sum": { "value": 244566.38072547672, "min": 2372.8602712855063, "max": 362195.66942273127, "count": 631 }, "SoccerTwos.Step.mean": { "value": 6389884.0, "min": 9982.0, "max": 6389884.0, "count": 639 }, "SoccerTwos.Step.sum": { "value": 6389884.0, "min": 9982.0, "max": 6389884.0, "count": 639 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.003226757748052478, "min": -0.12121902406215668, "max": 0.1877116858959198, "count": 639 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.5420953035354614, "min": -28.00159454345703, "max": 36.97920227050781, "count": 639 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0032982449047267437, "min": -0.12614789605140686, "max": 0.1865699142217636, "count": 639 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.5541051626205444, "min": -29.14016342163086, "max": 36.7542724609375, "count": 639 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 639 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 639 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.17651428637050448, "min": -0.7869333326816559, "max": 0.6341866610778703, "count": 639 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 29.65440011024475, "min": -54.91200006008148, "max": 55.27120041847229, "count": 639 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.17651428637050448, "min": -0.7869333326816559, "max": 0.6341866610778703, "count": 639 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 29.65440011024475, "min": -54.91200006008148, "max": 55.27120041847229, "count": 639 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 639 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 639 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012226999139723678, "min": 0.010700129181107817, "max": 0.023625865237166484, "count": 307 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012226999139723678, "min": 0.010700129181107817, "max": 0.023625865237166484, "count": 307 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10100149686137835, "min": 0.00040658007201272995, "max": 0.12078153441349665, "count": 307 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10100149686137835, "min": 0.00040658007201272995, "max": 0.12078153441349665, "count": 307 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10279191260536512, "min": 0.00039623022894375026, "max": 0.1227528507510821, "count": 307 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10279191260536512, "min": 0.00039623022894375026, "max": 0.1227528507510821, "count": 307 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 307 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 307 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 307 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 307 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 307 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 307 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684353327", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/kent/conda3/envs/rl-soccer2/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/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": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1684362960" }, "total": 9633.589431040004, "count": 1, "self": 0.0038056609919294715, "children": { "run_training.setup": { "total": 0.007691809005336836, "count": 1, "self": 0.007691809005336836 }, "TrainerController.start_learning": { "total": 9633.577933570006, "count": 1, "self": 6.980726071502431, "children": { "TrainerController._reset_env": { "total": 2.5145168869494228, "count": 32, "self": 2.5145168869494228 }, "TrainerController.advance": { "total": 9623.713544371552, "count": 437536, "self": 6.1688790749176405, "children": { "env_step": { "total": 7378.757593222574, "count": 437536, "self": 6198.510448100147, "children": { "SubprocessEnvManager._take_step": { "total": 1175.7724007374345, "count": 437536, "self": 32.29881483585632, "children": { "TorchPolicy.evaluate": { "total": 1143.4735859015782, "count": 807176, "self": 1143.4735859015782 } } }, "workers": { "total": 4.474744384991936, "count": 437536, "self": 0.0, "children": { "worker_root": { "total": 9618.226115238416, "count": 437536, "is_parallel": true, "self": 4240.423115636455, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0034081870107911527, "count": 2, "is_parallel": true, "self": 0.0005932310014031827, "children": { "_process_rank_one_or_two_observation": { "total": 0.00281495600938797, "count": 8, "is_parallel": true, "self": 0.00281495600938797 } } }, "UnityEnvironment.step": { "total": 0.026518134996877052, "count": 1, "is_parallel": true, "self": 0.0009760199900483713, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006545910000568256, "count": 1, "is_parallel": true, "self": 0.0006545910000568256 }, "communicator.exchange": { "total": 0.022079807007685304, "count": 1, "is_parallel": true, "self": 0.022079807007685304 }, "steps_from_proto": { "total": 0.0028077169990865514, "count": 2, "is_parallel": true, "self": 0.00042655297147575766, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023811640276107937, "count": 8, "is_parallel": true, "self": 0.0023811640276107937 } } } } } } }, "UnityEnvironment.step": { "total": 5377.716560485875, "count": 437535, "is_parallel": true, "self": 389.5137392156612, "children": { "UnityEnvironment._generate_step_input": { "total": 233.52408491376264, "count": 437535, "is_parallel": true, "self": 233.52408491376264 }, "communicator.exchange": { "total": 3662.8266292031767, "count": 437535, "is_parallel": true, "self": 3662.8266292031767 }, "steps_from_proto": { "total": 1091.8521071532741, "count": 875070, "is_parallel": true, "self": 158.82564080308657, "children": { "_process_rank_one_or_two_observation": { "total": 933.0264663501875, "count": 3500280, "is_parallel": true, "self": 933.0264663501875 } } } } }, "steps_from_proto": { "total": 0.08643911608669441, "count": 62, "is_parallel": true, "self": 0.012416926969308406, "children": { "_process_rank_one_or_two_observation": { "total": 0.074022189117386, "count": 248, "is_parallel": true, "self": 0.074022189117386 } } } } } } } } }, "trainer_advance": { "total": 2238.787072074061, "count": 437536, "self": 57.899110328624374, "children": { "process_trajectory": { "total": 657.2002860603534, "count": 437536, "self": 654.284158256356, "children": { "RLTrainer._checkpoint": { "total": 2.9161278039973695, "count": 12, "self": 2.9161278039973695 } } }, "_update_policy": { "total": 1523.6876756850834, "count": 308, "self": 765.2689602988976, "children": { "TorchPOCAOptimizer.update": { "total": 758.4187153861858, "count": 9210, "self": 758.4187153861858 } } } } } } }, "trainer_threads": { "total": 7.899943739175797e-07, "count": 1, "self": 7.899943739175797e-07 }, "TrainerController._save_models": { "total": 0.3691454500076361, "count": 1, "self": 0.0015013960073702037, "children": { "RLTrainer._checkpoint": { "total": 0.3676440540002659, "count": 1, "self": 0.3676440540002659 } } } } } } }