{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9078477621078491, "min": 1.9078477621078491, "max": 3.2957534790039062, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37973.80078125, "min": 24063.94140625, "max": 135596.03125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.297872340425535, "min": 42.12931034482759, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19664.0, "min": 12368.0, "max": 30216.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1555.2604386263408, "min": 1196.3403235093597, "max": 1560.8099373603118, "count": 436 }, "SoccerTwos.Self-play.ELO.sum": { "value": 292388.96246175206, "min": 2392.6806470187194, "max": 352381.6458665134, "count": 436 }, "SoccerTwos.Step.mean": { "value": 4999918.0, "min": 9650.0, "max": 4999918.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999918.0, "min": 9650.0, "max": 4999918.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0617896132171154, "min": -0.11058781296014786, "max": 0.18997271358966827, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 11.616447448730469, "min": -21.23076057434082, "max": 27.35607147216797, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06536415964365005, "min": -0.11063147336244583, "max": 0.1877618432044983, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 12.288461685180664, "min": -21.02396011352539, "max": 27.037704467773438, "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": 0.26304681123571194, "min": -0.5345200002193451, "max": 0.46133871136173127, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 49.45280051231384, "min": -57.226400315761566, "max": 57.206000208854675, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.26304681123571194, "min": -0.5345200002193451, "max": 0.46133871136173127, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 49.45280051231384, "min": -57.226400315761566, "max": 57.206000208854675, "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": 0.02201175633817911, "min": 0.008823668660867649, "max": 0.023307186791983743, "count": 238 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02201175633817911, "min": 0.008823668660867649, "max": 0.023307186791983743, "count": 238 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10789070874452591, "min": 8.463776287233789e-08, "max": 0.11757578973968824, "count": 238 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10789070874452591, "min": 8.463776287233789e-08, "max": 0.11757578973968824, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1093550369143486, "min": 1.119358176519351e-07, "max": 0.11974578822652499, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1093550369143486, "min": 1.119358176519351e-07, "max": 0.11974578822652499, "count": 238 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 238 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 238 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678297401", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\kikt\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwo --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1678311021" }, "total": 13620.1335727, "count": 1, "self": 0.22788170000239916, "children": { "run_training.setup": { "total": 0.09601550000000003, "count": 1, "self": 0.09601550000000003 }, "TrainerController.start_learning": { "total": 13619.809675499999, "count": 1, "self": 7.207703000351103, "children": { "TrainerController._reset_env": { "total": 4.227935299999947, "count": 25, "self": 4.227935299999947 }, "TrainerController.advance": { "total": 13608.241979799648, "count": 338125, "self": 7.185260799722528, "children": { "env_step": { "total": 5024.792374799936, "count": 338125, "self": 3903.417886999726, "children": { "SubprocessEnvManager._take_step": { "total": 1116.5868763998087, "count": 338125, "self": 37.91783839888717, "children": { "TorchPolicy.evaluate": { "total": 1078.6690380009215, "count": 634718, "self": 1078.6690380009215 } } }, "workers": { "total": 4.787611400401272, "count": 338125, "self": 0.0, "children": { "worker_root": { "total": 13607.81961760046, "count": 338125, "is_parallel": true, "self": 10508.101556100219, "children": { "steps_from_proto": { "total": 0.0346549000046763, "count": 50, "is_parallel": true, "self": 0.007636000001278287, "children": { "_process_rank_one_or_two_observation": { "total": 0.027018900003398016, "count": 200, "is_parallel": true, "self": 0.027018900003398016 } } }, "UnityEnvironment.step": { "total": 3099.6834066002366, "count": 338125, "is_parallel": true, "self": 143.06467950110118, "children": { "UnityEnvironment._generate_step_input": { "total": 119.27113220007513, "count": 338125, "is_parallel": true, "self": 119.27113220007513 }, "communicator.exchange": { "total": 2380.456225599538, "count": 338125, "is_parallel": true, "self": 2380.456225599538 }, "steps_from_proto": { "total": 456.8913692995223, "count": 676250, "is_parallel": true, "self": 99.78794519935235, "children": { "_process_rank_one_or_two_observation": { "total": 357.10342410016995, "count": 2705000, "is_parallel": true, "self": 357.10342410016995 } } } } } } } } } } }, "trainer_advance": { "total": 8576.26434419999, "count": 338125, "self": 50.20808540011603, "children": { "process_trajectory": { "total": 1122.7728492998715, "count": 338125, "self": 1121.6031140998703, "children": { "RLTrainer._checkpoint": { "total": 1.1697352000012415, "count": 10, "self": 1.1697352000012415 } } }, "_update_policy": { "total": 7403.283409500002, "count": 238, "self": 666.1272109999418, "children": { "TorchPOCAOptimizer.update": { "total": 6737.15619850006, "count": 7146, "self": 6737.15619850006 } } } } } } }, "trainer_threads": { "total": 6.999998731771484e-07, "count": 1, "self": 6.999998731771484e-07 }, "TrainerController._save_models": { "total": 0.13205670000024838, "count": 1, "self": 0.00586720000137575, "children": { "RLTrainer._checkpoint": { "total": 0.12618949999887263, "count": 1, "self": 0.12618949999887263 } } } } } } }