{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7411012649536133, "min": 1.6961510181427002, "max": 3.295753002166748, "count": 1252 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35156.31640625, "min": 12173.609375, "max": 168399.515625, "count": 1252 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.916666666666664, "min": 43.44642857142857, "max": 999.0, "count": 1252 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19124.0, "min": 15592.0, "max": 25196.0, "count": 1252 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1594.5067715172045, "min": 1171.6416466366177, "max": 1614.5563890795188, "count": 1082 }, "SoccerTwos.Self-play.ELO.sum": { "value": 267877.13761489035, "min": 2346.344797489375, "max": 358047.4440677434, "count": 1082 }, "SoccerTwos.Step.mean": { "value": 12519971.0, "min": 9616.0, "max": 12519971.0, "count": 1252 }, "SoccerTwos.Step.sum": { "value": 12519971.0, "min": 9616.0, "max": 12519971.0, "count": 1252 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02816130220890045, "min": -0.11008672416210175, "max": 0.1796835958957672, "count": 1252 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.759260177612305, "min": -19.780067443847656, "max": 23.424413681030273, "count": 1252 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02283097803592682, "min": -0.11071392148733139, "max": 0.18538567423820496, "count": 1252 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.8584351539611816, "min": -18.863433837890625, "max": 23.08604621887207, "count": 1252 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1252 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1252 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.070254435200663, "min": -0.6666666666666666, "max": 0.5283764705938452, "count": 1252 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -11.872999548912048, "min": -61.83880007266998, "max": 57.880599796772, "count": 1252 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.070254435200663, "min": -0.6666666666666666, "max": 0.5283764705938452, "count": 1252 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -11.872999548912048, "min": -61.83880007266998, "max": 57.880599796772, "count": 1252 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1252 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1252 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.021215014916379005, "min": 0.009693034209218847, "max": 0.02533264345806098, "count": 593 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.021215014916379005, "min": 0.009693034209218847, "max": 0.02533264345806098, "count": 593 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11411015391349792, "min": 1.4977959637008098e-07, "max": 0.11997421011328697, "count": 593 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11411015391349792, "min": 1.4977959637008098e-07, "max": 0.11997421011328697, "count": 593 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11599365373452504, "min": 1.6075619602891795e-07, "max": 0.12160344173510869, "count": 593 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11599365373452504, "min": 1.6075619602891795e-07, "max": 0.12160344173510869, "count": 593 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 593 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 593 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 593 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 593 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 593 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 593 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676312812", "python_version": "3.9.6 (default, Oct 18 2022, 12:41:40) \n[Clang 14.0.0 (clang-1400.0.29.202)]", "command_line_arguments": "/Users/fvelasco/data/venvs/hf_rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --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": "1676365476" }, "total": 52664.415812041996, "count": 1, "self": 0.15353174999472685, "children": { "run_training.setup": { "total": 0.02997491699999999, "count": 1, "self": 0.02997491699999999 }, "TrainerController.start_learning": { "total": 52664.232305375, "count": 1, "self": 8.909420470583427, "children": { "TrainerController._reset_env": { "total": 4.985777793006607, "count": 63, "self": 4.985777793006607 }, "TrainerController.advance": { "total": 52650.25667865341, "count": 837122, "self": 9.134196910708852, "children": { "env_step": { "total": 44169.76878383858, "count": 837122, "self": 42872.10296424802, "children": { "SubprocessEnvManager._take_step": { "total": 1291.7740297753348, "count": 837122, "self": 40.894040670202685, "children": { "TorchPolicy.evaluate": { "total": 1250.8799891051322, "count": 1596810, "self": 1250.8799891051322 } } }, "workers": { "total": 5.891789815227356, "count": 837121, "self": 0.0, "children": { "worker_root": { "total": 52646.573285942315, "count": 837121, "is_parallel": true, "self": 11043.512015397973, "children": { "steps_from_proto": { "total": 0.10091716498965564, "count": 126, "is_parallel": true, "self": 0.01139199597933227, "children": { "_process_rank_one_or_two_observation": { "total": 0.08952516901032337, "count": 504, "is_parallel": true, "self": 0.08952516901032337 } } }, "UnityEnvironment.step": { "total": 41602.96035337935, "count": 837121, "is_parallel": true, "self": 102.70439208157768, "children": { "UnityEnvironment._generate_step_input": { "total": 719.8941285679578, "count": 837121, "is_parallel": true, "self": 719.8941285679578 }, "communicator.exchange": { "total": 39348.54049803857, "count": 837121, "is_parallel": true, "self": 39348.54049803857 }, "steps_from_proto": { "total": 1431.8213346912394, "count": 1674242, "is_parallel": true, "self": 155.80288655441836, "children": { "_process_rank_one_or_two_observation": { "total": 1276.018448136821, "count": 6696968, "is_parallel": true, "self": 1276.018448136821 } } } } } } } } } } }, "trainer_advance": { "total": 8471.35369790412, "count": 837121, "self": 72.20356877518861, "children": { "process_trajectory": { "total": 1675.4860178489655, "count": 837121, "self": 1673.4690467239564, "children": { "RLTrainer._checkpoint": { "total": 2.0169711250091495, "count": 25, "self": 2.0169711250091495 } } }, "_update_policy": { "total": 6723.664111279966, "count": 593, "self": 1139.773801425922, "children": { "TorchPOCAOptimizer.update": { "total": 5583.890309854044, "count": 17796, "self": 5583.890309854044 } } } } } } }, "trainer_threads": { "total": 4.579997039400041e-07, "count": 1, "self": 4.579997039400041e-07 }, "TrainerController._save_models": { "total": 0.08042800000112038, "count": 1, "self": 0.0007107919955160469, "children": { "RLTrainer._checkpoint": { "total": 0.07971720800560433, "count": 1, "self": 0.07971720800560433 } } } } } } }