{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.591202735900879, "min": 1.576461672782898, "max": 3.295790672302246, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 63037.08984375, "min": 17617.28515625, "max": 957413.5, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 17.586206896551722, "min": 16.62230215827338, "max": 358.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18360.0, "min": 15132.0, "max": 24024.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1447.0320658846629, "min": 1154.6932713299086, "max": 1466.8112458584237, "count": 999 }, "SoccerTwos.Self-play.ELO.sum": { "value": 755350.738391794, "min": 7107.293939842906, "max": 814234.7723575226, "count": 999 }, "SoccerTwos.Step.mean": { "value": 9999995.0, "min": 9957.0, "max": 9999995.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999995.0, "min": 9957.0, "max": 9999995.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.015528060495853424, "min": -0.10294513404369354, "max": 0.18965570628643036, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 8.214344024658203, "min": -42.497703552246094, "max": 61.23341369628906, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.014794806018471718, "min": -0.10167635232210159, "max": 0.1922016590833664, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.826452255249023, "min": -42.01740264892578, "max": 59.716331481933594, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.04080340305663688, "min": -0.4218624997884035, "max": 0.48153333283132976, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 21.585000216960907, "min": -89.35180050134659, "max": 125.87880036234856, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.04080340305663688, "min": -0.4218624997884035, "max": 0.48153333283132976, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 21.585000216960907, "min": -89.35180050134659, "max": 125.87880036234856, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019490288386684065, "min": 0.01022618855155694, "max": 0.02483719602654067, "count": 484 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019490288386684065, "min": 0.01022618855155694, "max": 0.02483719602654067, "count": 484 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10220161899924278, "min": 0.00556322493745635, "max": 0.11632043123245239, "count": 484 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10220161899924278, "min": 0.00556322493745635, "max": 0.11632043123245239, "count": 484 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10278775369127592, "min": 0.005624144431203603, "max": 0.11713258946935336, "count": 484 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10278775369127592, "min": 0.005624144431203603, "max": 0.11713258946935336, "count": 484 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 1.205799397600006e-07, "min": 1.205799397600006e-07, "max": 0.00019958164020917997, "count": 484 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 1.205799397600006e-07, "min": 1.205799397600006e-07, "max": 0.00019958164020917997, "count": 484 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 484 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 484 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.6017976000000026e-05, "min": 1.6017976000000026e-05, "max": 0.009979102918000004, "count": 484 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.6017976000000026e-05, "min": 1.6017976000000026e-05, "max": 0.009979102918000004, "count": 484 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693333901", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/mgmeskill/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=Downstrike-10M --no-graphics --num-envs=32", "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": "1693346598" }, "total": 12696.901499327272, "count": 1, "self": 0.8128237212076783, "children": { "run_training.setup": { "total": 0.1724072340875864, "count": 1, "self": 0.1724072340875864 }, "TrainerController.start_learning": { "total": 12695.916268371977, "count": 1, "self": 4.1688310210593045, "children": { "TrainerController._reset_env": { "total": 146.85403133556247, "count": 495, "self": 146.85403133556247 }, "TrainerController.advance": { "total": 12544.567460204009, "count": 55699, "self": 1.6526970262639225, "children": { "env_step": { "total": 8165.541931728367, "count": 55699, "self": 2764.078356688842, "children": { "SubprocessEnvManager._take_step": { "total": 5394.85639378801, "count": 1601157, "self": 131.83333107223734, "children": { "TorchPolicy.evaluate": { "total": 5263.0230627157725, "count": 2932254, "self": 5263.0230627157725 } } }, "workers": { "total": 6.607181251514703, "count": 55699, "self": 0.0, "children": { "worker_root": { "total": 405506.96444705594, "count": 1599583, "is_parallel": true, "self": 386161.60350995045, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.07886765897274017, "count": 64, "is_parallel": true, "self": 0.0166148510761559, "children": { "_process_rank_one_or_two_observation": { "total": 0.06225280789658427, "count": 256, "is_parallel": true, "self": 0.06225280789658427 } } }, "UnityEnvironment.step": { "total": 0.7396135642193258, "count": 32, "is_parallel": true, "self": 0.020251302514225245, "children": { "UnityEnvironment._generate_step_input": { "total": 0.01759060798212886, "count": 32, "is_parallel": true, "self": 0.01759060798212886 }, "communicator.exchange": { "total": 0.645212515257299, "count": 32, "is_parallel": true, "self": 0.645212515257299 }, "steps_from_proto": { "total": 0.05655913846567273, "count": 64, "is_parallel": true, "self": 0.01000463031232357, "children": { "_process_rank_one_or_two_observation": { "total": 0.04655450815334916, "count": 256, "is_parallel": true, "self": 0.04655450815334916 } } } } } } }, "UnityEnvironment.step": { "total": 19305.8035399043, "count": 1599551, "is_parallel": true, "self": 1247.6211247742176, "children": { "UnityEnvironment._generate_step_input": { "total": 786.1591690224595, "count": 1599551, "is_parallel": true, "self": 786.1591690224595 }, "communicator.exchange": { "total": 13873.461208882276, "count": 1599551, "is_parallel": true, "self": 13873.461208882276 }, "steps_from_proto": { "total": 3398.562037225347, "count": 3199102, "is_parallel": true, "self": 576.9713781671599, "children": { "_process_rank_one_or_two_observation": { "total": 2821.590659058187, "count": 12796408, "is_parallel": true, "self": 2821.590659058187 } } } } }, "steps_from_proto": { "total": 39.557397201191634, "count": 31616, "is_parallel": true, "self": 6.698158380575478, "children": { "_process_rank_one_or_two_observation": { "total": 32.859238820616156, "count": 126464, "is_parallel": true, "self": 32.859238820616156 } } } } } } } } }, "trainer_advance": { "total": 4377.372831449378, "count": 55699, "self": 60.90775148430839, "children": { "process_trajectory": { "total": 2136.620560474228, "count": 55699, "self": 2135.02693261439, "children": { "RLTrainer._checkpoint": { "total": 1.593627859838307, "count": 5, "self": 1.593627859838307 } } }, "_update_policy": { "total": 2179.844519490842, "count": 484, "self": 1224.6795570533723, "children": { "TorchPOCAOptimizer.update": { "total": 955.1649624374695, "count": 14520, "self": 955.1649624374695 } } } } } } }, "trainer_threads": { "total": 5.513429641723633e-07, "count": 1, "self": 5.513429641723633e-07 }, "TrainerController._save_models": { "total": 0.3259452600032091, "count": 1, "self": 0.0019989372231066227, "children": { "RLTrainer._checkpoint": { "total": 0.3239463227801025, "count": 1, "self": 0.3239463227801025 } } } } } } }