{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.25303316116333, "min": 2.2181384563446045, "max": 2.333526849746704, "count": 22 }, "SoccerTwos.Policy.Entropy.sum": { "value": 47223.57421875, "min": 21176.81640625, "max": 49540.0234375, "count": 22 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.588235294117645, "min": 42.55102040816327, "max": 75.10606060606061, "count": 22 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19920.0, "min": 8340.0, "max": 20180.0, "count": 22 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1436.6850885574333, "min": 1420.957679346875, "max": 1445.1289760810987, "count": 22 }, "SoccerTwos.Self-play.ELO.sum": { "value": 244236.46505476366, "min": 139478.1277144495, "max": 283061.4419381178, "count": 22 }, "SoccerTwos.Step.mean": { "value": 3009978.0, "min": 2799997.0, "max": 3009978.0, "count": 22 }, "SoccerTwos.Step.sum": { "value": 3009978.0, "min": 2799997.0, "max": 3009978.0, "count": 22 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04858648031949997, "min": -0.06071087345480919, "max": 0.057406455278396606, "count": 22 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.211114883422852, "min": -8.211114883422852, "max": 9.586877822875977, "count": 22 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.051111526787281036, "min": -0.05901632457971573, "max": 0.05398515984416008, "count": 22 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -8.637847900390625, "min": -8.637847900390625, "max": 9.015522003173828, "count": 22 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 22 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 22 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08056568252969776, "min": -0.270185566440071, "max": 0.22813404525848144, "count": 22 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -13.615600347518921, "min": -26.20799994468689, "max": 42.88920050859451, "count": 22 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08056568252969776, "min": -0.270185566440071, "max": 0.22813404525848144, "count": 22 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -13.615600347518921, "min": -26.20799994468689, "max": 42.88920050859451, "count": 22 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 22 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 22 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01866164224144692, "min": 0.013299963200309625, "max": 0.021053528459742666, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01866164224144692, "min": 0.013299963200309625, "max": 0.021053528459742666, "count": 10 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1034640853603681, "min": 0.08911226640144984, "max": 0.10452298521995544, "count": 10 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1034640853603681, "min": 0.08911226640144984, "max": 0.10452298521995544, "count": 10 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10537167390187581, "min": 0.09102364853024483, "max": 0.10614525328079859, "count": 10 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10537167390187581, "min": 0.09102364853024483, "max": 0.10614525328079859, "count": 10 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 10 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 10 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 10 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 10 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 10 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675468324", "python_version": "3.10.4 (main, Jan 23 2023, 21:59:58) [Clang 14.0.0 (clang-1400.0.29.202)]", "command_line_arguments": "/Users/davidhajdu/.pyenv/versions/RL/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --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", "numpy_version": "1.21.2", "end_time_seconds": "1675469777" }, "total": 1452.8753001250006, "count": 1, "self": 0.15392699999938486, "children": { "run_training.setup": { "total": 0.01425879199814517, "count": 1, "self": 0.01425879199814517 }, "TrainerController.start_learning": { "total": 1452.7071143330031, "count": 1, "self": 0.1983301609288901, "children": { "TrainerController._reset_env": { "total": 1.8846464169982937, "count": 3, "self": 1.8846464169982937 }, "TrainerController.advance": { "total": 1450.4863115880798, "count": 14970, "self": 0.19549912325965124, "children": { "env_step": { "total": 1227.144114718143, "count": 14970, "self": 1196.0092934863278, "children": { "SubprocessEnvManager._take_step": { "total": 31.00468764469042, "count": 14970, "self": 0.9640196857399133, "children": { "TorchPolicy.evaluate": { "total": 30.040667958950507, "count": 27044, "self": 30.040667958950507 } } }, "workers": { "total": 0.13013358712487388, "count": 14969, "self": 0.0, "children": { "worker_root": { "total": 1450.3859152803452, "count": 14969, "is_parallel": true, "self": 283.8744217774729, "children": { "steps_from_proto": { "total": 0.007310874996619532, "count": 6, "is_parallel": true, "self": 0.0009484170041105244, "children": { "_process_rank_one_or_two_observation": { "total": 0.0063624579925090075, "count": 24, "is_parallel": true, "self": 0.0063624579925090075 } } }, "UnityEnvironment.step": { "total": 1166.5041826278757, "count": 14969, "is_parallel": true, "self": 2.887594155909028, "children": { "UnityEnvironment._generate_step_input": { "total": 20.931710134133027, "count": 14969, "is_parallel": true, "self": 20.931710134133027 }, "communicator.exchange": { "total": 1102.4025346820818, "count": 14969, "is_parallel": true, "self": 1102.4025346820818 }, "steps_from_proto": { "total": 40.2823436557519, "count": 29938, "is_parallel": true, "self": 4.493868864137767, "children": { "_process_rank_one_or_two_observation": { "total": 35.788474791614135, "count": 119752, "is_parallel": true, "self": 35.788474791614135 } } } } } } } } } } }, "trainer_advance": { "total": 223.1466977466771, "count": 14969, "self": 1.5573225504122092, "children": { "process_trajectory": { "total": 55.09537353026826, "count": 14969, "self": 54.94132548926791, "children": { "RLTrainer._checkpoint": { "total": 0.15404804100035108, "count": 1, "self": 0.15404804100035108 } } }, "_update_policy": { "total": 166.49400166599662, "count": 10, "self": 27.522364000957168, "children": { "TorchPOCAOptimizer.update": { "total": 138.97163766503945, "count": 300, "self": 138.97163766503945 } } } } } } }, "trainer_threads": { "total": 7.089984137564898e-07, "count": 1, "self": 7.089984137564898e-07 }, "TrainerController._save_models": { "total": 0.1378254579976783, "count": 1, "self": 0.0016826239952933975, "children": { "RLTrainer._checkpoint": { "total": 0.13614283400238492, "count": 1, "self": 0.13614283400238492 } } } } } } }