{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.822566032409668, "min": 1.7924662828445435, "max": 3.295607328414917, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35809.77734375, "min": 22087.16796875, "max": 118000.0625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.7125, "min": 41.279661016949156, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19428.0, "min": 11916.0, "max": 28128.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1566.5653456806922, "min": 1193.855767723958, "max": 1578.835491219127, "count": 488 }, "SoccerTwos.Self-play.ELO.sum": { "value": 250650.45530891075, "min": 2390.585739003281, "max": 347165.07309874066, "count": 488 }, "SoccerTwos.Step.mean": { "value": 4999990.0, "min": 9082.0, "max": 4999990.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999990.0, "min": 9082.0, "max": 4999990.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.010300255380570889, "min": -0.10910031944513321, "max": 0.17050983011722565, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.6480408906936646, "min": -20.40176010131836, "max": 25.61324691772461, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.009193485602736473, "min": -0.10899746417999268, "max": 0.16702477633953094, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.4709577560424805, "min": -20.382526397705078, "max": 25.9049072265625, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09465125054121018, "min": -0.5777411741368911, "max": 0.51398621756455, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -15.144200086593628, "min": -57.36560010910034, "max": 62.688000202178955, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09465125054121018, "min": -0.5777411741368911, "max": 0.51398621756455, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -15.144200086593628, "min": -57.36560010910034, "max": 62.688000202178955, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012749818619340658, "min": 0.011668509912366669, "max": 0.022843901254236697, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012749818619340658, "min": 0.011668509912366669, "max": 0.022843901254236697, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09577699949344, "min": 6.519637172459624e-05, "max": 0.11873191570242246, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09577699949344, "min": 6.519637172459624e-05, "max": 0.11873191570242246, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09710122446219126, "min": 6.327543972777979e-05, "max": 0.12073325614134471, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09710122446219126, "min": 6.327543972777979e-05, "max": 0.12073325614134471, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680246955", "python_version": "3.9.16 (main, Mar 1 2023, 18:22:10) \n[GCC 11.2.0]", "command_line_arguments": "ml-agents/mlagents/trainers/learn.py ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680257145" }, "total": 10189.94834217, "count": 1, "self": 0.44507462399997166, "children": { "run_training.setup": { "total": 0.05366480899999715, "count": 1, "self": 0.05366480899999715 }, "TrainerController.start_learning": { "total": 10189.449602737, "count": 1, "self": 7.733716013133744, "children": { "TrainerController._reset_env": { "total": 4.038401389997603, "count": 25, "self": 4.038401389997603 }, "TrainerController.advance": { "total": 10177.428206385868, "count": 341700, "self": 8.054457054160594, "children": { "env_step": { "total": 7882.810816224602, "count": 341700, "self": 6405.537656605702, "children": { "SubprocessEnvManager._take_step": { "total": 1472.6588848649405, "count": 341700, "self": 50.20280604509912, "children": { "TorchPolicy.evaluate": { "total": 1422.4560788198414, "count": 630824, "self": 1422.4560788198414 } } }, "workers": { "total": 4.614274753958853, "count": 341700, "self": 0.0, "children": { "worker_root": { "total": 10169.498118034508, "count": 341700, "is_parallel": true, "self": 4725.862021528441, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003004491999945458, "count": 2, "is_parallel": true, "self": 0.0008788069998217907, "children": { "_process_rank_one_or_two_observation": { "total": 0.002125685000123667, "count": 8, "is_parallel": true, "self": 0.002125685000123667 } } }, "UnityEnvironment.step": { "total": 0.04222155900004054, "count": 1, "is_parallel": true, "self": 0.0012354030001233696, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008995069999855332, "count": 1, "is_parallel": true, "self": 0.0008995069999855332 }, "communicator.exchange": { "total": 0.03673596299995552, "count": 1, "is_parallel": true, "self": 0.03673596299995552 }, "steps_from_proto": { "total": 0.003350685999976122, "count": 2, "is_parallel": true, "self": 0.000635942000144496, "children": { "_process_rank_one_or_two_observation": { "total": 0.002714743999831626, "count": 8, "is_parallel": true, "self": 0.002714743999831626 } } } } } } }, "UnityEnvironment.step": { "total": 5443.591706503065, "count": 341699, "is_parallel": true, "self": 357.7160711808456, "children": { "UnityEnvironment._generate_step_input": { "total": 249.56928493024895, "count": 341699, "is_parallel": true, "self": 249.56928493024895 }, "communicator.exchange": { "total": 3801.1887028055644, "count": 341699, "is_parallel": true, "self": 3801.1887028055644 }, "steps_from_proto": { "total": 1035.1176475864063, "count": 683398, "is_parallel": true, "self": 197.87877202872846, "children": { "_process_rank_one_or_two_observation": { "total": 837.2388755576778, "count": 2733592, "is_parallel": true, "self": 837.2388755576778 } } } } }, "steps_from_proto": { "total": 0.044390003000899014, "count": 48, "is_parallel": true, "self": 0.009421320011597345, "children": { "_process_rank_one_or_two_observation": { "total": 0.03496868298930167, "count": 192, "is_parallel": true, "self": 0.03496868298930167 } } } } } } } } }, "trainer_advance": { "total": 2286.5629331071054, "count": 341700, "self": 59.07281249302605, "children": { "process_trajectory": { "total": 845.6958294960875, "count": 341700, "self": 843.1716562320873, "children": { "RLTrainer._checkpoint": { "total": 2.524173264000183, "count": 10, "self": 2.524173264000183 } } }, "_update_policy": { "total": 1381.7942911179916, "count": 240, "self": 935.5972647249785, "children": { "TorchPOCAOptimizer.update": { "total": 446.1970263930132, "count": 7209, "self": 446.1970263930132 } } } } } } }, "trainer_threads": { "total": 1.3810004020342603e-06, "count": 1, "self": 1.3810004020342603e-06 }, "TrainerController._save_models": { "total": 0.2492775669998082, "count": 1, "self": 0.0019719709998753387, "children": { "RLTrainer._checkpoint": { "total": 0.24730559599993285, "count": 1, "self": 0.24730559599993285 } } } } } } }