{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4040422439575195, "min": 1.389272689819336, "max": 1.6866295337677002, "count": 3784 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31001.251953125, "min": 21323.73046875, "max": 48199.7109375, "count": 3784 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.46666666666667, "min": 39.19672131147541, "max": 103.59183673469387, "count": 3784 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19608.0, "min": 13972.0, "max": 21516.0, "count": 3784 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1679.1014325918177, "min": 1632.7613784935306, "max": 1727.6244567850686, "count": 3784 }, "SoccerTwos.Self-play.ELO.sum": { "value": 302238.2578665272, "min": 162289.07697266375, "max": 412682.45444266696, "count": 3784 }, "SoccerTwos.Step.mean": { "value": 101669974.0, "min": 63839957.0, "max": 101669974.0, "count": 3784 }, "SoccerTwos.Step.sum": { "value": 101669974.0, "min": 63839957.0, "max": 101669974.0, "count": 3784 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04738142713904381, "min": -0.1338440179824829, "max": 0.07649713009595871, "count": 3784 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.528656959533691, "min": -23.824234008789062, "max": 12.163043975830078, "count": 3784 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04632115736603737, "min": -0.13657046854496002, "max": 0.07525458186864853, "count": 3784 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -8.337808609008789, "min": -24.30954360961914, "max": 11.965478897094727, "count": 3784 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3784 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3784 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.20810666547881232, "min": -0.46046404423338644, "max": 0.3727172958223443, "count": 3784 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -37.45919978618622, "min": -81.96259987354279, "max": 50.07079994678497, "count": 3784 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.20810666547881232, "min": -0.46046404423338644, "max": 0.3727172958223443, "count": 3784 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -37.45919978618622, "min": -81.96259987354279, "max": 50.07079994678497, "count": 3784 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3784 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3784 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012447048083413393, "min": 0.006253487911050115, "max": 0.018026918790807638, "count": 920 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012447048083413393, "min": 0.006253487911050115, "max": 0.018026918790807638, "count": 920 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09590630009770393, "min": 0.08399255201220512, "max": 0.11452940801779429, "count": 920 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09590630009770393, "min": 0.08399255201220512, "max": 0.11452940801779429, "count": 920 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09688987210392952, "min": 0.08464914709329605, "max": 0.11564263626933098, "count": 920 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09688987210392952, "min": 0.08464914709329605, "max": 0.11564263626933098, "count": 920 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00017804190225271285, "min": 0.00017804190225271285, "max": 0.0002233511727496176, "count": 920 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00017804190225271285, "min": 0.00017804190225271285, "max": 0.0002233511727496176, "count": 920 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.15934728720000005, "min": 0.15934728720000005, "max": 0.17445038239999996, "count": 920 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.15934728720000005, "min": 0.15934728720000005, "max": 0.17445038239999996, "count": 920 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.00297142963128, "min": 0.00297142963128, "max": 0.003725074081759999, "count": 920 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.00297142963128, "min": 0.00297142963128, "max": 0.003725074081759999, "count": 920 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678158026", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\hecto\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=Marcus_Aurelius --no-graphics --num-envs=3 --resume", "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": "1678221000" }, "total": 62974.878135, "count": 1, "self": 0.7530789000011282, "children": { "run_training.setup": { "total": 0.23405830000000005, "count": 1, "self": 0.23405830000000005 }, "TrainerController.start_learning": { "total": 62973.8909978, "count": 1, "self": 56.54999989740463, "children": { "TrainerController._reset_env": { "total": 9.2083191999738, "count": 191, "self": 9.2083191999738 }, "TrainerController.advance": { "total": 62907.91292920262, "count": 2341995, "self": 54.95805009851756, "children": { "env_step": { "total": 14380.168186204846, "count": 2341995, "self": 6056.160596902182, "children": { "SubprocessEnvManager._take_step": { "total": 8294.715488901744, "count": 2635335, "self": 345.6244872133566, "children": { "TorchPolicy.evaluate": { "total": 7949.091001688387, "count": 4795270, "self": 7949.091001688387 } } }, "workers": { "total": 29.292100400920724, "count": 2341995, "self": 0.0, "children": { "worker_root": { "total": 188692.60285562044, "count": 2635048, "is_parallel": true, "self": 163069.1211460244, "children": { "steps_from_proto": { "total": 0.8392588000379639, "count": 1142, "is_parallel": true, "self": 0.17484940014436479, "children": { "_process_rank_one_or_two_observation": { "total": 0.6644093998935992, "count": 4568, "is_parallel": true, "self": 0.6644093998935992 } } }, "UnityEnvironment.step": { "total": 25622.642450795996, "count": 2635048, "is_parallel": true, "self": 1347.3915643958098, "children": { "UnityEnvironment._generate_step_input": { "total": 1021.1517150005162, "count": 2635048, "is_parallel": true, "self": 1021.1517150005162 }, "communicator.exchange": { "total": 19333.650508797786, "count": 2635048, "is_parallel": true, "self": 19333.650508797786 }, "steps_from_proto": { "total": 3920.4486626018825, "count": 5270096, "is_parallel": true, "self": 820.3554068026206, "children": { "_process_rank_one_or_two_observation": { "total": 3100.093255799262, "count": 21080384, "is_parallel": true, "self": 3100.093255799262 } } } } } } } } } } }, "trainer_advance": { "total": 48472.78669289925, "count": 2341995, "self": 452.41372810120083, "children": { "process_trajectory": { "total": 8908.12789859808, "count": 2341995, "self": 8901.109465898058, "children": { "RLTrainer._checkpoint": { "total": 7.018432700022117, "count": 76, "self": 7.018432700022117 } } }, "_update_policy": { "total": 39112.24506619997, "count": 921, "self": 5357.371810299046, "children": { "TorchPOCAOptimizer.update": { "total": 33754.87325590092, "count": 27619, "self": 33754.87325590092 } } } } } } }, "trainer_threads": { "total": 1.7999991541728377e-06, "count": 1, "self": 1.7999991541728377e-06 }, "TrainerController._save_models": { "total": 0.21974770000088029, "count": 1, "self": 0.02153800000087358, "children": { "RLTrainer._checkpoint": { "total": 0.1982097000000067, "count": 1, "self": 0.1982097000000067 } } } } } } }