{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.5095441937446594, "min": 0.487953245639801, "max": 0.7500085830688477, "count": 13134 }, "SoccerTwos.Policy.Entropy.sum": { "value": 22159.05859375, "min": 5755.7138671875, "max": 34133.51171875, "count": 13134 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 31.437908496732025, "min": 25.371584699453553, "max": 114.8048780487805, "count": 13134 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19240.0, "min": 16040.0, "max": 22816.0, "count": 13134 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1798.6028407771905, "min": 1756.9619587826037, "max": 1857.4125701764967, "count": 13134 }, "SoccerTwos.Self-play.ELO.sum": { "value": 550372.4692778203, "min": 147720.75203913188, "max": 678978.8305315933, "count": 13134 }, "SoccerTwos.Step.mean": { "value": 423909960.0, "min": 292579994.0, "max": 423909960.0, "count": 13134 }, "SoccerTwos.Step.sum": { "value": 423909960.0, "min": 292579994.0, "max": 423909960.0, "count": 13134 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.022518029436469078, "min": -0.09095162153244019, "max": 0.06672990322113037, "count": 13134 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.958071231842041, "min": -25.011695861816406, "max": 16.768901824951172, "count": 13134 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02337733842432499, "min": -0.09311029314994812, "max": 0.06788720935583115, "count": 13134 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.223597526550293, "min": -25.605331420898438, "max": 16.67617416381836, "count": 13134 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 13134 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 13134 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.03231715307266581, "min": -0.5423760689221896, "max": 0.4325039974848429, "count": 13134 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.986000299453735, "min": -82.38359987735748, "max": 70.85119926929474, "count": 13134 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.03231715307266581, "min": -0.5423760689221896, "max": 0.4325039974848429, "count": 13134 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.986000299453735, "min": -82.38359987735748, "max": 70.85119926929474, "count": 13134 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 13134 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 13134 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.010125669335078176, "min": 0.005079278784493605, "max": 0.012585793458856642, "count": 1599 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.010125669335078176, "min": 0.005079278784493605, "max": 0.012585793458856642, "count": 1599 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07386725346247355, "min": 0.05883044364551703, "max": 0.08806271577874819, "count": 1599 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07386725346247355, "min": 0.05883044364551703, "max": 0.08806271577874819, "count": 1599 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07418720747033755, "min": 0.059075573831796645, "max": 0.0883685993651549, "count": 1599 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07418720747033755, "min": 0.059075573831796645, "max": 0.0883685993651549, "count": 1599 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 4.5669289976931565e-05, "min": 4.5669289976931565e-05, "max": 0.00012440825253060196, "count": 1599 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 4.5669289976931565e-05, "min": 4.5669289976931565e-05, "max": 0.00012440825253060196, "count": 1599 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1599 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1599 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0009218617971600001, "min": 0.0009218617971600001, "max": 0.0024940169402000007, "count": 1599 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0009218617971600001, "min": 0.0009218617971600001, "max": 0.0024940169402000007, "count": 1599 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681832799", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/data/qyh/env/ml-agents/bin/mlagents-learn ./results3/configuration.yaml", "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": "1682001277" }, "total": 168478.0871106279, "count": 1, "self": 0.08574602054432034, "children": { "run_training.setup": { "total": 0.14052101410925388, "count": 1, "self": 0.14052101410925388 }, "TrainerController.start_learning": { "total": 168477.86084359325, "count": 1, "self": 64.52053452469409, "children": { "TrainerController._reset_env": { "total": 191.4930366766639, "count": 658, "self": 191.4930366766639 }, "TrainerController.advance": { "total": 168221.35228842404, "count": 798993, "self": 37.37655054870993, "children": { "env_step": { "total": 90276.28782155924, "count": 798993, "self": 31598.287695226725, "children": { "SubprocessEnvManager._take_step": { "total": 58589.91419728752, "count": 9705898, "self": 1664.615275001619, "children": { "TorchPolicy.evaluate": { "total": 56925.2989222859, "count": 17708576, "self": 56925.2989222859 } } }, "workers": { "total": 88.085929044988, "count": 798993, "self": 0.0, "children": { "worker_root": { "total": 2744719.3191467817, "count": 9703491, "is_parallel": true, "self": 2529001.305475149, "children": { "run_training.setup": { "total": 2.248336225748062, "count": 16, "is_parallel": true, "self": 1.6485097352415323, "children": { "steps_from_proto": { "total": 0.06190275540575385, "count": 24, "is_parallel": true, "self": 0.014613636303693056, "children": { "_process_rank_one_or_two_observation": { "total": 0.047289119102060795, "count": 96, "is_parallel": true, "self": 0.047289119102060795 } } }, "UnityEnvironment.step": { "total": 0.537923735100776, "count": 12, "is_parallel": true, "self": 0.015022579580545425, "children": { "UnityEnvironment._generate_step_input": { "total": 0.011497851461172104, "count": 12, "is_parallel": true, "self": 0.011497851461172104 }, "communicator.exchange": { "total": 0.4681625687517226, "count": 12, "is_parallel": true, "self": 0.4681625687517226 }, "steps_from_proto": { "total": 0.043240735307335854, "count": 24, "is_parallel": true, "self": 0.008981929160654545, "children": { "_process_rank_one_or_two_observation": { "total": 0.03425880614668131, "count": 96, "is_parallel": true, "self": 0.03425880614668131 } } } } } } }, "steps_from_proto": { "total": 51.12376921251416, "count": 21024, "is_parallel": true, "self": 8.68344674212858, "children": { "_process_rank_one_or_two_observation": { "total": 42.44032247038558, "count": 84096, "is_parallel": true, "self": 42.44032247038558 } } }, "UnityEnvironment.step": { "total": 215664.6415661946, "count": 9703463, "is_parallel": true, "self": 14011.687235515565, "children": { "UnityEnvironment._generate_step_input": { "total": 8825.06509437412, "count": 9703463, "is_parallel": true, "self": 8825.06509437412 }, "communicator.exchange": { "total": 152440.38248000015, "count": 9703463, "is_parallel": true, "self": 152440.38248000015 }, "steps_from_proto": { "total": 40387.50675630476, "count": 19406926, "is_parallel": true, "self": 7472.986082323361, "children": { "_process_rank_one_or_two_observation": { "total": 32914.5206739814, "count": 77627704, "is_parallel": true, "self": 32914.5206739814 } } } } }, "TrainerController.start_learning": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "TrainerController._reset_env": { "total": 141.03239501267672, "count": 192, "is_parallel": true, "self": 141.03239501267672 }, "TrainerController.advance": { "total": 50740.379378035665, "count": 196848, "is_parallel": true, "self": 11.320737347006798, "children": { "env_step": { "total": 26179.858498170972, "count": 196848, "is_parallel": true, "self": 9692.619662202429, "children": { "SubprocessEnvManager._take_step": { "total": 16460.434454098344, "count": 2463488, "is_parallel": true, "self": 502.05509485304356, "children": { "TorchPolicy.evaluate": { "total": 15958.3793592453, "count": 4443200, "is_parallel": true, "self": 15958.3793592453 } } }, "workers": { "total": 25.88871542364359, "count": 196848, "is_parallel": true, "self": 0.0, "children": { "worker_root": { "total": 813677.3323606402, "count": 2462704, "is_parallel": true, "self": 760764.4309295416, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.9904440864920616, "count": 384, "is_parallel": true, "self": 0.2338181808590889, "children": { "_process_rank_one_or_two_observation": { "total": 0.7566259056329727, "count": 1536, "is_parallel": true, "self": 0.7566259056329727 } } }, "UnityEnvironment.step": { "total": 8.606779761612415, "count": 192, "is_parallel": true, "self": 0.2403612732887268, "children": { "UnityEnvironment._generate_step_input": { "total": 0.18396562337875366, "count": 192, "is_parallel": true, "self": 0.18396562337875366 }, "communicator.exchange": { "total": 7.490601100027561, "count": 192, "is_parallel": true, "self": 7.490601100027561 }, "steps_from_proto": { "total": 0.6918517649173737, "count": 384, "is_parallel": true, "self": 0.14371086657047272, "children": { "_process_rank_one_or_two_observation": { "total": 0.5481408983469009, "count": 1536, "is_parallel": true, "self": 0.5481408983469009 } } } } } } }, "steps_from_proto": { "total": 11.298283137381077, "count": 5632, "is_parallel": true, "self": 2.0631723180413246, "children": { "_process_rank_one_or_two_observation": { "total": 9.235110819339752, "count": 22528, "is_parallel": true, "self": 9.235110819339752 } } }, "UnityEnvironment.step": { "total": 52901.6031479612, "count": 2462512, "is_parallel": true, "self": 3145.9382705688477, "children": { "UnityEnvironment._generate_step_input": { "total": 2053.6538956984878, "count": 2462512, "is_parallel": true, "self": 2053.6538956984878 }, "communicator.exchange": { "total": 38531.16309039295, "count": 2462512, "is_parallel": true, "self": 38531.16309039295 }, "steps_from_proto": { "total": 9170.847891300917, "count": 4925024, "is_parallel": true, "self": 1796.9766098037362, "children": { "_process_rank_one_or_two_observation": { "total": 7373.8712814971805, "count": 19700096, "is_parallel": true, "self": 7373.8712814971805 } } } } } } } } }, "steps_from_proto": { "total": 0.11512628570199013, "count": 32, "is_parallel": true, "self": 0.024500152561813593, "children": { "_process_rank_one_or_two_observation": { "total": 0.09062613314017653, "count": 128, "is_parallel": true, "self": 0.09062613314017653 } } }, "UnityEnvironment.step": { "total": 0.8005401608534157, "count": 16, "is_parallel": true, "self": 0.033204701729118824, "children": { "UnityEnvironment._generate_step_input": { "total": 0.01916773756965995, "count": 16, "is_parallel": true, "self": 0.01916773756965995 }, "communicator.exchange": { "total": 0.6606826134957373, "count": 16, "is_parallel": true, "self": 0.6606826134957373 }, "steps_from_proto": { "total": 0.08748510805889964, "count": 32, "is_parallel": true, "self": 0.014867117162793875, "children": { "_process_rank_one_or_two_observation": { "total": 0.07261799089610577, "count": 128, "is_parallel": true, "self": 0.07261799089610577 } } } } } } }, "trainer_advance": { "total": 24549.200142517686, "count": 196848, "is_parallel": true, "self": 554.96931347996, "children": { "process_trajectory": { "total": 10709.801105678082, "count": 196848, "is_parallel": true, "self": 10702.898002944887, "children": { "RLTrainer._checkpoint": { "total": 6.903102733194828, "count": 16, "is_parallel": true, "self": 6.903102733194828 } } }, "_update_policy": { "total": 13284.429723359644, "count": 400, "is_parallel": true, "self": 9254.43152333796, "children": { "TorchPOCAOptimizer.update": { "total": 4029.998200021684, "count": 12000, "is_parallel": true, "self": 4029.998200021684 } } } } } } } } } } } } } } }, "trainer_advance": { "total": 77907.68791631609, "count": 798992, "self": 1418.5711116055027, "children": { "process_trajectory": { "total": 33053.75368895708, "count": 798992, "self": 33028.48213754501, "children": { "RLTrainer._checkpoint": { "total": 25.271551412064582, "count": 65, "self": 25.271551412064582 } } }, "_update_policy": { "total": 43435.36311575351, "count": 1599, "self": 30128.70112026343, "children": { "TorchPOCAOptimizer.update": { "total": 13306.661995490082, "count": 47970, "self": 13306.661995490082 } } } } } } }, "trainer_threads": { "total": 2.4167820811271667e-06, "count": 1, "self": 2.4167820811271667e-06 }, "TrainerController._save_models": { "total": 0.49498155107721686, "count": 1, "self": 0.0033433022908866405, "children": { "RLTrainer._checkpoint": { "total": 0.4916382487863302, "count": 1, "self": 0.4916382487863302 } } } } } } }