{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4226882457733154, "min": 1.3962759971618652, "max": 3.221355676651001, "count": 1380 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31003.22265625, "min": 17583.181640625, "max": 117620.5625, "count": 1380 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.775, "min": 37.41085271317829, "max": 999.0, "count": 1380 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19448.0, "min": 720.0, "max": 31968.0, "count": 1380 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1664.2310724196864, "min": 1197.9743045436578, "max": 1685.6221675923723, "count": 1366 }, "SoccerTwos.Self-play.ELO.sum": { "value": 266276.97158714983, "min": 2395.9486090873156, "max": 414599.35986528243, "count": 1366 }, "SoccerTwos.Step.mean": { "value": 15019960.0, "min": 1219955.0, "max": 15019960.0, "count": 1381 }, "SoccerTwos.Step.sum": { "value": 15019960.0, "min": 1219955.0, "max": 15019960.0, "count": 1381 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04060524329543114, "min": -0.11362434923648834, "max": 0.14808301627635956, "count": 1381 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.456233978271484, "min": -20.059688568115234, "max": 19.550342559814453, "count": 1381 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03960680216550827, "min": -0.11319874227046967, "max": 0.15150688588619232, "count": 1381 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.297481536865234, "min": -21.028011322021484, "max": 19.544387817382812, "count": 1381 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1381 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1381 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.023240252110943105, "min": -0.5631809539738155, "max": 0.8185999989509583, "count": 1381 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.6952000856399536, "min": -61.11840009689331, "max": 44.8549998998642, "count": 1381 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.023240252110943105, "min": -0.5631809539738155, "max": 0.8185999989509583, "count": 1381 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.6952000856399536, "min": -61.11840009689331, "max": 44.8549998998642, "count": 1381 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1381 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1381 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016539275362932433, "min": 0.011099975449421132, "max": 0.025155503421168155, "count": 666 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016539275362932433, "min": 0.011099975449421132, "max": 0.025155503421168155, "count": 666 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10412231087684631, "min": 6.601868826692226e-05, "max": 0.12981368551651637, "count": 666 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10412231087684631, "min": 6.601868826692226e-05, "max": 0.12981368551651637, "count": 666 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10583755721648534, "min": 6.635894211891961e-05, "max": 0.13248267372449238, "count": 666 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10583755721648534, "min": 6.635894211891961e-05, "max": 0.13248267372449238, "count": 666 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 666 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 666 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 666 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 666 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 666 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 666 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687892781", "python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/philippehenrisaade/miniconda3/envs/hfrl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-4 --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687935481" }, "total": 42699.583049661, "count": 1, "self": 0.20594733899633866, "children": { "run_training.setup": { "total": 0.018065414999995255, "count": 1, "self": 0.018065414999995255 }, "TrainerController.start_learning": { "total": 42699.359036907, "count": 1, "self": 31.80477599411097, "children": { "TrainerController._reset_env": { "total": 3.755812973002172, "count": 70, "self": 3.755812973002172 }, "TrainerController.advance": { "total": 42663.5523152869, "count": 949028, "self": 34.32809844633448, "children": { "env_step": { "total": 19083.95156357178, "count": 949028, "self": 15436.484321485323, "children": { "SubprocessEnvManager._take_step": { "total": 3627.9598752196785, "count": 949028, "self": 166.5173499370867, "children": { "TorchPolicy.evaluate": { "total": 3461.4425252825918, "count": 1736418, "self": 3461.4425252825918 } } }, "workers": { "total": 19.507366866778582, "count": 949028, "self": 0.0, "children": { "worker_root": { "total": 42640.89260341357, "count": 949028, "is_parallel": true, "self": 30391.48658158106, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035533710000024143, "count": 2, "is_parallel": true, "self": 0.0009003320000005033, "children": { "_process_rank_one_or_two_observation": { "total": 0.002653039000001911, "count": 8, "is_parallel": true, "self": 0.002653039000001911 } } }, "UnityEnvironment.step": { "total": 0.0279442670000023, "count": 1, "is_parallel": true, "self": 0.0009846460000062507, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004360929999975838, "count": 1, "is_parallel": true, "self": 0.0004360929999975838 }, "communicator.exchange": { "total": 0.02342329100000029, "count": 1, "is_parallel": true, "self": 0.02342329100000029 }, "steps_from_proto": { "total": 0.003100236999998174, "count": 2, "is_parallel": true, "self": 0.0006361289999929909, "children": { "_process_rank_one_or_two_observation": { "total": 0.002464108000005183, "count": 8, "is_parallel": true, "self": 0.002464108000005183 } } } } } } }, "steps_from_proto": { "total": 0.1469940020244067, "count": 138, "is_parallel": true, "self": 0.031021074054386588, "children": { "_process_rank_one_or_two_observation": { "total": 0.11597292797002012, "count": 552, "is_parallel": true, "self": 0.11597292797002012 } } }, "UnityEnvironment.step": { "total": 12249.259027830489, "count": 949027, "is_parallel": true, "self": 619.4764606847712, "children": { "UnityEnvironment._generate_step_input": { "total": 445.8712582004788, "count": 949027, "is_parallel": true, "self": 445.8712582004788 }, "communicator.exchange": { "total": 9272.433666667364, "count": 949027, "is_parallel": true, "self": 9272.433666667364 }, "steps_from_proto": { "total": 1911.4776422778743, "count": 1898054, "is_parallel": true, "self": 412.73713850096715, "children": { "_process_rank_one_or_two_observation": { "total": 1498.7405037769072, "count": 7592216, "is_parallel": true, "self": 1498.7405037769072 } } } } } } } } } } }, "trainer_advance": { "total": 23545.27265326879, "count": 949028, "self": 213.41046612054924, "children": { "process_trajectory": { "total": 3981.8585847302465, "count": 949028, "self": 3975.6349691592236, "children": { "RLTrainer._checkpoint": { "total": 6.223615571022833, "count": 28, "self": 6.223615571022833 } } }, "_update_policy": { "total": 19350.003602417994, "count": 667, "self": 2491.647260686168, "children": { "TorchPOCAOptimizer.update": { "total": 16858.356341731826, "count": 20004, "self": 16858.356341731826 } } } } } } }, "trainer_threads": { "total": 1.4389952411875129e-06, "count": 1, "self": 1.4389952411875129e-06 }, "TrainerController._save_models": { "total": 0.24613121399306692, "count": 1, "self": 0.0018452409931342117, "children": { "RLTrainer._checkpoint": { "total": 0.2442859729999327, "count": 1, "self": 0.2442859729999327 } } } } } } }