{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.479475498199463, "min": 1.44920814037323, "max": 3.2870302200317383, "count": 6218 }, "SoccerTwos.Policy.Entropy.sum": { "value": 297457.4375, "min": 289377.875, "max": 933561.3125, "count": 6218 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.34788029925187, "min": 52.02969247083775, "max": 934.3396226415094, "count": 6218 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 196804.0, "min": 195076.0, "max": 205980.0, "count": 6218 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1779.570455061751, "min": 1200.213260185901, "max": 1806.4025421207928, "count": 6218 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2854431.0099190488, "min": 19345.487705959662, "max": 3210556.3445862844, "count": 6218 }, "SoccerTwos.Step.mean": { "value": 621799876.0, "min": 99130.0, "max": 621799876.0, "count": 6218 }, "SoccerTwos.Step.sum": { "value": 621799876.0, "min": 99130.0, "max": 621799876.0, "count": 6218 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.01865948736667633, "min": -0.07774338126182556, "max": 0.29597318172454834, "count": 6218 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 29.92981719970703, "min": -112.5280990600586, "max": 525.9443359375, "count": 6218 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.018179278820753098, "min": -0.07759729027748108, "max": 0.29505228996276855, "count": 6218 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 29.159563064575195, "min": -112.7722396850586, "max": 524.3079223632812, "count": 6218 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 6218 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 6218 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.007097755955936308, "min": -0.2379181282213557, "max": 0.5599306692014467, "count": 6218 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 11.384800553321838, "min": -321.1480002999306, "max": 994.9967991709709, "count": 6218 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.007097755955936308, "min": -0.2379181282213557, "max": 0.5599306692014467, "count": 6218 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 11.384800553321838, "min": -321.1480002999306, "max": 994.9967991709709, "count": 6218 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018677117116846297, "min": 0.014004342342862705, "max": 0.022986856099711683, "count": 6218 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.09338558558423149, "min": 0.05601736937145082, "max": 0.11493428049855842, "count": 6218 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.06978202119469643, "min": 0.0006221189043778643, "max": 0.07562727654973665, "count": 6218 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.3489101059734821, "min": 0.0024884756175114573, "max": 0.3781363827486833, "count": 6218 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07015919208526611, "min": 0.0006226879464182992, "max": 0.07596947535872459, "count": 6218 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.35079596042633054, "min": 0.002490751785673197, "max": 0.37984737679362296, "count": 6218 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0001268524976090636, "min": 0.0001268524976090636, "max": 0.00019999257094489102, "count": 6218 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.000634262488045318, "min": 0.0005076473299411141, "max": 0.000999852613956046, "count": 6218 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 6218 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 1.25, "min": 1.0, "max": 1.25, "count": 6218 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.006346280428712941, "min": 0.006346280428712941, "max": 0.009999628918511765, "count": 6218 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.03173140214356471, "min": 0.025396976829047062, "max": 0.04999263806342353, "count": 6218 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6218 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6218 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682568970", "python_version": "3.9.16 (main, Apr 26 2023, 09:57:11) \n[GCC 9.4.0]", "command_line_arguments": "/home/isaac/python_envs/py3916_env/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "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": "1683006014" }, "total": 437043.68475484505, "count": 1, "self": 0.7130158360232599, "children": { "run_training.setup": { "total": 0.037868824001634493, "count": 1, "self": 0.037868824001634493 }, "TrainerController.start_learning": { "total": 437042.93387018505, "count": 1, "self": 504.2119189830264, "children": { "TrainerController._reset_env": { "total": 129.67054323881166, "count": 3108, "self": 129.67054323881166 }, "TrainerController.advance": { "total": 436407.8497430352, "count": 21543167, "self": 462.50987240840914, "children": { "env_step": { "total": 226138.94783080448, "count": 21543167, "self": 77472.67399612421, "children": { "SubprocessEnvManager._take_step": { "total": 148335.14884961658, "count": 43282980, "self": 4455.659547170537, "children": { "TorchPolicy.evaluate": { "total": 143879.48930244605, "count": 79270246, "self": 143879.48930244605 } } }, "workers": { "total": 331.1249850636814, "count": 21543166, "self": 0.0, "children": { "worker_root": { "total": 1744848.1302099233, "count": 43277862, "is_parallel": true, "self": 1431101.705132508, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0065239280520472676, "count": 8, "is_parallel": true, "self": 0.001548569998703897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0049753580533433706, "count": 32, "is_parallel": true, "self": 0.0049753580533433706 } } }, "UnityEnvironment.step": { "total": 0.06651191902346909, "count": 4, "is_parallel": true, "self": 0.0019736990216188133, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00165824600844644, "count": 4, "is_parallel": true, "self": 0.00165824600844644 }, "communicator.exchange": { "total": 0.056721621978795156, "count": 4, "is_parallel": true, "self": 0.056721621978795156 }, "steps_from_proto": { "total": 0.006158352014608681, "count": 8, "is_parallel": true, "self": 0.0013875370495952666, "children": { "_process_rank_one_or_two_observation": { "total": 0.004770814965013415, "count": 32, "is_parallel": true, "self": 0.004770814965013415 } } } } } } }, "UnityEnvironment.step": { "total": 313727.4256338962, "count": 43277858, "is_parallel": true, "self": 17884.11739179684, "children": { "UnityEnvironment._generate_step_input": { "total": 14195.086262234632, "count": 43277858, "is_parallel": true, "self": 14195.086262234632 }, "communicator.exchange": { "total": 222924.1463174398, "count": 43277858, "is_parallel": true, "self": 222924.1463174398 }, "steps_from_proto": { "total": 58724.07566242496, "count": 86555716, "is_parallel": true, "self": 12865.930516250024, "children": { "_process_rank_one_or_two_observation": { "total": 45858.14514617494, "count": 346222864, "is_parallel": true, "self": 45858.14514617494 } } } } }, "steps_from_proto": { "total": 18.9994435190456, "count": 24856, "is_parallel": true, "self": 3.978966613445664, "children": { "_process_rank_one_or_two_observation": { "total": 15.020476905599935, "count": 99424, "is_parallel": true, "self": 15.020476905599935 } } } } } } } } }, "trainer_advance": { "total": 209806.39203982236, "count": 21543166, "self": 4925.422231000091, "children": { "process_trajectory": { "total": 83878.85316192245, "count": 21543166, "self": 83811.24159167602, "children": { "RLTrainer._checkpoint": { "total": 67.61157024643035, "count": 310, "self": 67.61157024643035 } } }, "_update_policy": { "total": 121002.11664689981, "count": 30163, "self": 83211.995876478, "children": { "TorchPOCAOptimizer.update": { "total": 37790.12077042181, "count": 904923, "self": 37790.12077042181 } } } } } } }, "TrainerController._save_models": { "total": 1.2016649279976264, "count": 1, "self": 0.007750097080133855, "children": { "RLTrainer._checkpoint": { "total": 1.1939148309174925, "count": 1, "self": 1.1939148309174925 } } } } } } }