{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4715203046798706, "min": 1.450524926185608, "max": 3.2957208156585693, "count": 1349 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27311.416015625, "min": 6500.7763671875, "max": 112942.0625, "count": 1349 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.91139240506329, "min": 41.810344827586206, "max": 999.0, "count": 1349 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19248.0, "min": 3996.0, "max": 31476.0, "count": 1349 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1633.7630491457198, "min": 1190.81306429258, "max": 1674.353935592132, "count": 1324 }, "SoccerTwos.Self-play.ELO.sum": { "value": 258134.56176502374, "min": 2381.62612858516, "max": 384412.792531291, "count": 1324 }, "SoccerTwos.Step.mean": { "value": 13489917.0, "min": 9124.0, "max": 13489917.0, "count": 1349 }, "SoccerTwos.Step.sum": { "value": 13489917.0, "min": 9124.0, "max": 13489917.0, "count": 1349 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.09469994157552719, "min": -0.11845909804105759, "max": 0.16957607865333557, "count": 1349 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -15.057291030883789, "min": -19.2597713470459, "max": 24.0902099609375, "count": 1349 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09920581430196762, "min": -0.12321903556585312, "max": 0.1633630245923996, "count": 1349 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -15.773724555969238, "min": -19.122188568115234, "max": 24.026042938232422, "count": 1349 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1349 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1349 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.199137105132049, "min": -0.6167000010609627, "max": 0.46511453084456617, "count": 1349 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -31.66279971599579, "min": -62.93199980258942, "max": 58.30740034580231, "count": 1349 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.199137105132049, "min": -0.6167000010609627, "max": 0.46511453084456617, "count": 1349 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -31.66279971599579, "min": -62.93199980258942, "max": 58.30740034580231, "count": 1349 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1349 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1349 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016598315542796626, "min": 0.010099395599293832, "max": 0.02617170734059376, "count": 650 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016598315542796626, "min": 0.010099395599293832, "max": 0.02617170734059376, "count": 650 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1116062785188357, "min": 2.0480440639403243e-06, "max": 0.12350986252228419, "count": 650 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1116062785188357, "min": 2.0480440639403243e-06, "max": 0.12350986252228419, "count": 650 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11325699786345164, "min": 2.2552148720933475e-06, "max": 0.1265305275718371, "count": 650 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11325699786345164, "min": 2.2552148720933475e-06, "max": 0.1265305275718371, "count": 650 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 650 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 650 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 650 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 650 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 650 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 650 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679292035", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\17723\\anconda_3\\envs\\rl3\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/mlagents/training-envs-executables/SoccerTwos --run-id=SoccerTwos3 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.12.1+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1679311086" }, "total": 19051.9107751, "count": 1, "self": 0.15190639999855193, "children": { "run_training.setup": { "total": 0.06460090000000007, "count": 1, "self": 0.06460090000000007 }, "TrainerController.start_learning": { "total": 19051.6942678, "count": 1, "self": 16.27303060029226, "children": { "TrainerController._reset_env": { "total": 4.163365299998364, "count": 68, "self": 4.163365299998364 }, "TrainerController.advance": { "total": 19031.04265229971, "count": 926483, "self": 16.982015299232444, "children": { "env_step": { "total": 13642.363800001165, "count": 926483, "self": 8303.997022900698, "children": { "SubprocessEnvManager._take_step": { "total": 5328.648837799872, "count": 926483, "self": 101.08632479912012, "children": { "TorchPolicy.evaluate": { "total": 5227.562513000752, "count": 1700404, "self": 5227.562513000752 } } }, "workers": { "total": 9.717939300595443, "count": 926483, "self": 0.0, "children": { "worker_root": { "total": 19025.142885899673, "count": 926483, "is_parallel": true, "self": 12309.342948199523, "children": { "steps_from_proto": { "total": 0.07659219999835809, "count": 136, "is_parallel": true, "self": 0.015100400003018155, "children": { "_process_rank_one_or_two_observation": { "total": 0.061491799995339935, "count": 544, "is_parallel": true, "self": 0.061491799995339935 } } }, "UnityEnvironment.step": { "total": 6715.723345500153, "count": 926483, "is_parallel": true, "self": 316.8574164990423, "children": { "UnityEnvironment._generate_step_input": { "total": 210.22225039903367, "count": 926483, "is_parallel": true, "self": 210.22225039903367 }, "communicator.exchange": { "total": 5254.63778020078, "count": 926483, "is_parallel": true, "self": 5254.63778020078 }, "steps_from_proto": { "total": 934.0058984012974, "count": 1852966, "is_parallel": true, "self": 189.24724460020514, "children": { "_process_rank_one_or_two_observation": { "total": 744.7586538010922, "count": 7411864, "is_parallel": true, "self": 744.7586538010922 } } } } } } } } } } }, "trainer_advance": { "total": 5371.696836999314, "count": 926483, "self": 113.92905559895189, "children": { "process_trajectory": { "total": 2616.7261714003553, "count": 926483, "self": 2611.1648458003583, "children": { "RLTrainer._checkpoint": { "total": 5.561325599996962, "count": 26, "self": 5.561325599996962 } } }, "_update_policy": { "total": 2641.0416100000066, "count": 651, "self": 1350.7592552000035, "children": { "TorchPOCAOptimizer.update": { "total": 1290.282354800003, "count": 19542, "self": 1290.282354800003 } } } } } } }, "trainer_threads": { "total": 6.999980541877449e-07, "count": 1, "self": 6.999980541877449e-07 }, "TrainerController._save_models": { "total": 0.21521890000076382, "count": 1, "self": 0.0025214999986928888, "children": { "RLTrainer._checkpoint": { "total": 0.21269740000207094, "count": 1, "self": 0.21269740000207094 } } } } } } }