{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6846721172332764, "min": 1.642417550086975, "max": 1.7495955228805542, "count": 65 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33208.2578125, "min": 3914.28466796875, "max": 37723.71875, "count": 65 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.24050632911393, "min": 51.333333333333336, "max": 87.22413793103448, "count": 65 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19668.0, "min": 616.0, "max": 20536.0, "count": 65 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1564.6653538545172, "min": 1538.3647519963977, "max": 1583.64657879535, "count": 65 }, "SoccerTwos.Self-play.ELO.sum": { "value": 247217.1259090137, "min": 9297.856345338925, "max": 291203.02268383966, "count": 65 }, "SoccerTwos.Step.mean": { "value": 6999867.0, "min": 6359971.0, "max": 6999867.0, "count": 65 }, "SoccerTwos.Step.sum": { "value": 6999867.0, "min": 6359971.0, "max": 6999867.0, "count": 65 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.006649640388786793, "min": -0.07206380367279053, "max": 0.09839209914207458, "count": 65 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.0506432056427002, "min": -12.611165046691895, "max": 9.354903221130371, "count": 65 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006710930727422237, "min": -0.07163926959037781, "max": 0.09823451191186905, "count": 65 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.0603270530700684, "min": -12.536871910095215, "max": 9.093672752380371, "count": 65 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 65 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 65 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.10880253020721146, "min": -0.25762857232775005, "max": 0.9501599907875061, "count": 65 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 17.19079977273941, "min": -45.08500015735626, "max": 38.47160005569458, "count": 65 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.10880253020721146, "min": -0.25762857232775005, "max": 0.9501599907875061, "count": 65 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 17.19079977273941, "min": -45.08500015735626, "max": 38.47160005569458, "count": 65 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 65 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 65 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014570843905676156, "min": 0.008831154210686995, "max": 0.022886693896725773, "count": 31 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014570843905676156, "min": 0.008831154210686995, "max": 0.022886693896725773, "count": 31 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09991522828737895, "min": 0.08965741445620855, "max": 0.10992061247428259, "count": 31 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09991522828737895, "min": 0.08965741445620855, "max": 0.10992061247428259, "count": 31 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10087271754940351, "min": 0.09077408388257027, "max": 0.11132331440846126, "count": 31 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10087271754940351, "min": 0.09077408388257027, "max": 0.11132331440846126, "count": 31 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 31 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 31 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 31 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 31 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 31 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 31 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681661840", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "F:\\Anaconda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1681664787" }, "total": 2947.4071331, "count": 1, "self": 0.4167561000003843, "children": { "run_training.setup": { "total": 0.38027100000000047, "count": 1, "self": 0.38027100000000047 }, "TrainerController.start_learning": { "total": 2946.6101059999996, "count": 1, "self": 1.5571050000007745, "children": { "TrainerController._reset_env": { "total": 18.48911449999989, "count": 4, "self": 18.48911449999989 }, "TrainerController.advance": { "total": 2926.3107052999994, "count": 44010, "self": 1.661134700002549, "children": { "env_step": { "total": 1262.0793885000105, "count": 44010, "self": 1016.2488215000345, "children": { "SubprocessEnvManager._take_step": { "total": 244.7850545999615, "count": 44010, "self": 9.610479599939538, "children": { "TorchPolicy.evaluate": { "total": 235.17457500002197, "count": 80290, "self": 235.17457500002197 } } }, "workers": { "total": 1.0455124000144664, "count": 44010, "self": 0.0, "children": { "worker_root": { "total": 2925.344063099998, "count": 44010, "is_parallel": true, "self": 2089.684665400033, "children": { "steps_from_proto": { "total": 0.009005899999767308, "count": 8, "is_parallel": true, "self": 0.0019428000003252066, "children": { "_process_rank_one_or_two_observation": { "total": 0.007063099999442102, "count": 32, "is_parallel": true, "self": 0.007063099999442102 } } }, "UnityEnvironment.step": { "total": 835.6503917999654, "count": 44010, "is_parallel": true, "self": 44.446412999955896, "children": { "UnityEnvironment._generate_step_input": { "total": 30.047285699988542, "count": 44010, "is_parallel": true, "self": 30.047285699988542 }, "communicator.exchange": { "total": 614.9665898000111, "count": 44010, "is_parallel": true, "self": 614.9665898000111 }, "steps_from_proto": { "total": 146.19010330000987, "count": 88020, "is_parallel": true, "self": 28.46912629991745, "children": { "_process_rank_one_or_two_observation": { "total": 117.72097700009242, "count": 352080, "is_parallel": true, "self": 117.72097700009242 } } } } } } } } } } }, "trainer_advance": { "total": 1662.5701820999861, "count": 44010, "self": 10.641407299972116, "children": { "process_trajectory": { "total": 278.1096203000132, "count": 44010, "self": 277.0344316000131, "children": { "RLTrainer._checkpoint": { "total": 1.0751887000001261, "count": 2, "self": 1.0751887000001261 } } }, "_update_policy": { "total": 1373.8191545000009, "count": 31, "self": 119.96183369999812, "children": { "TorchPOCAOptimizer.update": { "total": 1253.8573208000028, "count": 930, "self": 1253.8573208000028 } } } } } } }, "trainer_threads": { "total": 1.0999997357430402e-06, "count": 1, "self": 1.0999997357430402e-06 }, "TrainerController._save_models": { "total": 0.2531801000000087, "count": 1, "self": 0.05682420000039201, "children": { "RLTrainer._checkpoint": { "total": 0.19635589999961667, "count": 1, "self": 0.19635589999961667 } } } } } } }