| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.335242509841919, | |
| "min": 1.2497478723526, | |
| "max": 1.65972900390625, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 25807.568359375, | |
| "min": 10785.5888671875, | |
| "max": 37479.4296875, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 60.28915662650602, | |
| "min": 41.96491228070175, | |
| "max": 127.0, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 20016.0, | |
| "min": 4132.0, | |
| "max": 21648.0, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1684.106472585243, | |
| "min": 1534.9586645687386, | |
| "max": 1720.918212215921, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 279561.67444915033, | |
| "min": 78232.41097047081, | |
| "max": 391619.8340776406, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 49999916.0, | |
| "min": 19849972.0, | |
| "max": 49999916.0, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 49999916.0, | |
| "min": 19849972.0, | |
| "max": 49999916.0, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.00577916344627738, | |
| "min": -0.1655862182378769, | |
| "max": 0.11256951093673706, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -0.9593411684036255, | |
| "min": -36.26338195800781, | |
| "max": 19.361955642700195, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.005254586227238178, | |
| "min": -0.16391198337078094, | |
| "max": 0.11621252447366714, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -0.8722612857818604, | |
| "min": -35.896724700927734, | |
| "max": 19.988554000854492, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.13476626341601453, | |
| "min": -0.4538626866554146, | |
| "max": 0.359811628280684, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -22.37119972705841, | |
| "min": -72.66999995708466, | |
| "max": 62.75700056552887, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.13476626341601453, | |
| "min": -0.4538626866554146, | |
| "max": 0.359811628280684, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -22.37119972705841, | |
| "min": -72.66999995708466, | |
| "max": 62.75700056552887, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 3016 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.01790835737483576, | |
| "min": 0.010325214187226569, | |
| "max": 0.02559798234530414, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.01790835737483576, | |
| "min": 0.010325214187226569, | |
| "max": 0.02559798234530414, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.10707559213042259, | |
| "min": 0.07452068577210108, | |
| "max": 0.13027308781941732, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.10707559213042259, | |
| "min": 0.07452068577210108, | |
| "max": 0.13027308781941732, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.10860733091831207, | |
| "min": 0.07558782448371251, | |
| "max": 0.13306420942147573, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.10860733091831207, | |
| "min": 0.07558782448371251, | |
| "max": 0.13306420942147573, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 1463 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 1463 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1677488444", | |
| "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", | |
| "command_line_arguments": "D:\\ProgramData\\anaconda3\\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": "1.13.1+cu117", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1677557751" | |
| }, | |
| "total": 69302.9482449, | |
| "count": 1, | |
| "self": 0.3338330000115093, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.09748789999999996, | |
| "count": 1, | |
| "self": 0.09748789999999996 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 69302.516924, | |
| "count": 1, | |
| "self": 54.97918619780103, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 10.728283500000272, | |
| "count": 152, | |
| "self": 10.728283500000272 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 69236.48009080222, | |
| "count": 2084404, | |
| "self": 60.12522281125712, | |
| "children": { | |
| "env_step": { | |
| "total": 50163.952168593896, | |
| "count": 2084404, | |
| "self": 30355.319812292288, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 19777.416134604282, | |
| "count": 2084404, | |
| "self": 361.2965211059782, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 19416.119613498304, | |
| "count": 3783858, | |
| "self": 19416.119613498304 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 31.216221697326382, | |
| "count": 2084404, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 69201.5203579982, | |
| "count": 2084404, | |
| "is_parallel": true, | |
| "self": 44271.920437604196, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.23890029995652817, | |
| "count": 304, | |
| "is_parallel": true, | |
| "self": 0.05334309982871677, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.1855572001278114, | |
| "count": 1216, | |
| "is_parallel": true, | |
| "self": 0.1855572001278114 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 24929.361020094053, | |
| "count": 2084404, | |
| "is_parallel": true, | |
| "self": 954.357082805036, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 835.8253819955305, | |
| "count": 2084404, | |
| "is_parallel": true, | |
| "self": 835.8253819955305 | |
| }, | |
| "communicator.exchange": { | |
| "total": 20064.6166544992, | |
| "count": 2084404, | |
| "is_parallel": true, | |
| "self": 20064.6166544992 | |
| }, | |
| "steps_from_proto": { | |
| "total": 3074.561900794286, | |
| "count": 4168808, | |
| "is_parallel": true, | |
| "self": 671.429250614442, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 2403.132650179844, | |
| "count": 16675232, | |
| "is_parallel": true, | |
| "self": 2403.132650179844 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 19012.402699397066, | |
| "count": 2084404, | |
| "self": 393.61732959251094, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 9976.830412104677, | |
| "count": 2084404, | |
| "self": 9956.102462904686, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 20.727949199990974, | |
| "count": 61, | |
| "self": 20.727949199990974 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 8641.954957699878, | |
| "count": 1463, | |
| "self": 4842.044250799509, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 3799.9107069003685, | |
| "count": 43890, | |
| "self": 3799.9107069003685 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.3999961083754897e-06, | |
| "count": 1, | |
| "self": 1.3999961083754897e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.3293620999902487, | |
| "count": 1, | |
| "self": 0.004451099986908957, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.3249110000033397, | |
| "count": 1, | |
| "self": 0.3249110000033397 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |