{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9140218496322632, "min": 1.8841967582702637, "max": 3.2789859771728516, "count": 493 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35707.9921875, "min": 27597.958984375, "max": 104927.5546875, "count": 493 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.95652173913044, "min": 43.792792792792795, "max": 999.0, "count": 493 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19308.0, "min": 2168.0, "max": 28124.0, "count": 493 }, "SoccerTwos.Self-play.ELO.mean": { "value": 2052.649160655305, "min": 1634.0065845004867, "max": 2081.739670231482, "count": 492 }, "SoccerTwos.Self-play.ELO.sum": { "value": 283265.58417043206, "min": 3274.644846055666, "max": 427167.9675037724, "count": 492 }, "SoccerTwos.Step.mean": { "value": 9999998.0, "min": 5079036.0, "max": 9999998.0, "count": 493 }, "SoccerTwos.Step.sum": { "value": 9999998.0, "min": 5079036.0, "max": 9999998.0, "count": 493 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.025618843734264374, "min": -0.12070416659116745, "max": 0.20378956198692322, "count": 493 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.535400390625, "min": -21.968158721923828, "max": 26.109474182128906, "count": 493 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03210558369755745, "min": -0.1224394366145134, "max": 0.20375539362430573, "count": 493 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.430570602416992, "min": -22.283977508544922, "max": 24.444137573242188, "count": 493 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 493 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 493 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1318231881528661, "min": -0.5799142860230946, "max": 0.6240606050599705, "count": 493 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -18.19159996509552, "min": -65.19880020618439, "max": 56.38820028305054, "count": 493 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1318231881528661, "min": -0.5799142860230946, "max": 0.6240606050599705, "count": 493 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -18.19159996509552, "min": -65.19880020618439, "max": 56.38820028305054, "count": 493 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 493 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 493 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016820453786446404, "min": 0.014308929060765271, "max": 0.02052879839708718, "count": 119 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016820453786446404, "min": 0.014308929060765271, "max": 0.02052879839708718, "count": 119 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09343656189739705, "min": 0.0028034542279783635, "max": 0.10124819080034891, "count": 119 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09343656189739705, "min": 0.0028034542279783635, "max": 0.10124819080034891, "count": 119 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09621581559379895, "min": 0.0031789839442353694, "max": 0.10505046372612317, "count": 119 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09621581559379895, "min": 0.0031789839442353694, "max": 0.10505046372612317, "count": 119 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00029500000000000007, "min": 0.00029500000000000007, "max": 0.00029500000000000007, "count": 119 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00029500000000000007, "min": 0.00029500000000000007, "max": 0.00029500000000000007, "count": 119 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999993, "min": 0.19999999999999993, "max": 0.19999999999999993, "count": 119 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999993, "min": 0.19999999999999993, "max": 0.19999999999999993, "count": 119 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 119 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 119 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689504139", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\84908\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos2 --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1689546902" }, "total": 42762.9120158, "count": 1, "self": 1.1350629000007757, "children": { "run_training.setup": { "total": 0.15489059999999988, "count": 1, "self": 0.15489059999999988 }, "TrainerController.start_learning": { "total": 42761.6220623, "count": 1, "self": 14.43110979921039, "children": { "TrainerController._reset_env": { "total": 6.812163500008067, "count": 21, "self": 6.812163500008067 }, "TrainerController.advance": { "total": 42740.09502890078, "count": 335812, "self": 13.688751599562238, "children": { "env_step": { "total": 11367.246411900505, "count": 335812, "self": 8355.052144300767, "children": { "SubprocessEnvManager._take_step": { "total": 3002.7884803989355, "count": 335812, "self": 97.30393870023727, "children": { "TorchPolicy.evaluate": { "total": 2905.484541698698, "count": 618688, "self": 2905.484541698698 } } }, "workers": { "total": 9.405787200801747, "count": 335812, "self": 0.0, "children": { "worker_root": { "total": 42735.313393801036, "count": 335812, "is_parallel": true, "self": 36066.35230810146, "children": { "steps_from_proto": { "total": 0.07878310001497724, "count": 42, "is_parallel": true, "self": 0.014979500020485759, "children": { "_process_rank_one_or_two_observation": { "total": 0.06380359999449148, "count": 168, "is_parallel": true, "self": 0.06380359999449148 } } }, "UnityEnvironment.step": { "total": 6668.882302599564, "count": 335812, "is_parallel": true, "self": 415.1706843983875, "children": { "UnityEnvironment._generate_step_input": { "total": 341.1210921979196, "count": 335812, "is_parallel": true, "self": 341.1210921979196 }, "communicator.exchange": { "total": 4620.200526800538, "count": 335812, "is_parallel": true, "self": 4620.200526800538 }, "steps_from_proto": { "total": 1292.389999202719, "count": 671624, "is_parallel": true, "self": 248.6019459020622, "children": { "_process_rank_one_or_two_observation": { "total": 1043.7880533006569, "count": 2686496, "is_parallel": true, "self": 1043.7880533006569 } } } } } } } } } } }, "trainer_advance": { "total": 31359.159865400714, "count": 335812, "self": 101.92826570027319, "children": { "process_trajectory": { "total": 4188.981500100416, "count": 335812, "self": 4185.253818100407, "children": { "RLTrainer._checkpoint": { "total": 3.7276820000088264, "count": 10, "self": 3.7276820000088264 } } }, "_update_policy": { "total": 27068.250099600024, "count": 119, "self": 1198.192632999806, "children": { "TorchPOCAOptimizer.update": { "total": 25870.057466600218, "count": 7140, "self": 25870.057466600218 } } } } } } }, "trainer_threads": { "total": 2.0000006770715117e-06, "count": 1, "self": 2.0000006770715117e-06 }, "TrainerController._save_models": { "total": 0.2837580999985221, "count": 1, "self": 0.00894529999641236, "children": { "RLTrainer._checkpoint": { "total": 0.2748128000021097, "count": 1, "self": 0.2748128000021097 } } } } } } }