| { | |
| "name": "root", | |
| "gauges": { | |
| "DungeonEscape.Policy.Entropy.mean": { | |
| "value": 0.7387705445289612, | |
| "min": 0.47643986344337463, | |
| "max": 0.963077187538147, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.Entropy.sum": { | |
| "value": 44270.0859375, | |
| "min": 19316.052734375, | |
| "max": 57795.2265625, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Environment.EpisodeLength.mean": { | |
| "value": 29.690537084398976, | |
| "min": 29.25568468923699, | |
| "max": 51.92042440318303, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Environment.EpisodeLength.sum": { | |
| "value": 58045.0, | |
| "min": 20170.0, | |
| "max": 61799.0, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Step.mean": { | |
| "value": 19979994.0, | |
| "min": 1319967.0, | |
| "max": 19979994.0, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Step.sum": { | |
| "value": 19979994.0, | |
| "min": 1319967.0, | |
| "max": 19979994.0, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.7170155048370361, | |
| "min": 0.4537115693092346, | |
| "max": 0.7238806486129761, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 1488.524169921875, | |
| "min": 291.70721435546875, | |
| "max": 1514.08251953125, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.7190065979957581, | |
| "min": 0.45914435386657715, | |
| "max": 0.7242827415466309, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 1492.65771484375, | |
| "min": 295.56463623046875, | |
| "max": 1519.375, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.ExtrinsicReward.mean": { | |
| "value": 0.6005115089514067, | |
| "min": 0.42398884239888424, | |
| "max": 0.618756936736959, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.ExtrinsicReward.sum": { | |
| "value": 1174.0, | |
| "min": 212.0, | |
| "max": 1192.0, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.9072642967542504, | |
| "min": 0.5705244122965641, | |
| "max": 0.923777961888981, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Environment.GroupCumulativeReward.sum": { | |
| "value": 1174.0, | |
| "min": 212.0, | |
| "max": 1192.0, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Losses.PolicyLoss.mean": { | |
| "value": 0.025970765251097164, | |
| "min": 0.02003467489654819, | |
| "max": 0.02940388735021568, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Losses.PolicyLoss.sum": { | |
| "value": 0.15582459150658298, | |
| "min": 0.04384033279493451, | |
| "max": 0.17642332410129408, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Losses.ValueLoss.mean": { | |
| "value": 0.007493831320769257, | |
| "min": 0.006882970143730442, | |
| "max": 0.012657495976115266, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Losses.ValueLoss.sum": { | |
| "value": 0.04496298792461554, | |
| "min": 0.025314991952230533, | |
| "max": 0.07474336146066586, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Losses.BaselineLoss.mean": { | |
| "value": 0.0073994019935424956, | |
| "min": 0.007087137286240855, | |
| "max": 0.011768768857129743, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Losses.BaselineLoss.sum": { | |
| "value": 0.044396411961254975, | |
| "min": 0.023281445292135078, | |
| "max": 0.07061261314277846, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.LearningRate.sum": { | |
| "value": 0.0017999999999999997, | |
| "min": 0.0006, | |
| "max": 0.0017999999999999997, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.Epsilon.mean": { | |
| "value": 0.2000000000000001, | |
| "min": 0.20000000000000007, | |
| "max": 0.2000000000000001, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.Epsilon.sum": { | |
| "value": 1.2000000000000006, | |
| "min": 0.40000000000000013, | |
| "max": 1.2000000000000006, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.Beta.mean": { | |
| "value": 0.010000000000000002, | |
| "min": 0.010000000000000002, | |
| "max": 0.010000000000000002, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.Policy.Beta.sum": { | |
| "value": 0.06000000000000001, | |
| "min": 0.020000000000000004, | |
| "max": 0.06000000000000001, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 312 | |
| }, | |
| "DungeonEscape.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 312 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1734446699", | |
| "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", | |
| "command_line_arguments": "\\\\?\\C:\\anaconda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/DungeonEscape.yaml --env=./training-envs-executables/DungeonEscape/UnityEnvironment.exe --run-id=DungeonEscape --no-graphics --resume", | |
| "mlagents_version": "1.2.0.dev0", | |
| "mlagents_envs_version": "1.2.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.5.1+cpu", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1734474139" | |
| }, | |
| "total": 27436.995059499997, | |
| "count": 1, | |
| "self": 0.3181868999963626, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.1388437999994494, | |
| "count": 1, | |
| "self": 0.1388437999994494 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 27436.5380288, | |
| "count": 1, | |
| "self": 21.926181698567234, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 8.739799100001619, | |
| "count": 1, | |
| "self": 8.739799100001619 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 27405.812782101428, | |
| "count": 948274, | |
| "self": 18.10939840339779, | |
| "children": { | |
| "env_step": { | |
| "total": 9457.995401397598, | |
| "count": 948274, | |
| "self": 8518.083113295848, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 927.308839501331, | |
| "count": 948274, | |
| "self": 53.046044098589846, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 874.2627954027412, | |
| "count": 815033, | |
| "self": 874.2627954027412 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 12.603448600419142, | |
| "count": 948274, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 27404.168480200235, | |
| "count": 948274, | |
| "is_parallel": true, | |
| "self": 20618.923279797527, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.005296400000588619, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0009778000003279885, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.004318600000260631, | |
| "count": 6, | |
| "is_parallel": true, | |
| "self": 0.004318600000260631 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 6785.239904002707, | |
| "count": 948274, | |
| "is_parallel": true, | |
| "self": 394.1696912051757, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 298.55590379998284, | |
| "count": 948274, | |
| "is_parallel": true, | |
| "self": 298.55590379998284 | |
| }, | |
| "communicator.exchange": { | |
| "total": 4872.826279197372, | |
| "count": 948274, | |
| "is_parallel": true, | |
| "self": 4872.826279197372 | |
| }, | |
| "steps_from_proto": { | |
| "total": 1219.688029800176, | |
| "count": 948274, | |
| "is_parallel": true, | |
| "self": 189.64897849756017, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 1030.039051302616, | |
| "count": 5689644, | |
| "is_parallel": true, | |
| "self": 1030.039051302616 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 17929.70798230043, | |
| "count": 948274, | |
| "self": 40.4367261020634, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 5760.006832598403, | |
| "count": 948274, | |
| "self": 5757.721544298418, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 2.285288299985041, | |
| "count": 38, | |
| "self": 2.285288299985041 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 12129.264423599965, | |
| "count": 1818, | |
| "self": 3112.0907305996734, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 9017.173693000292, | |
| "count": 54540, | |
| "self": 9017.173693000292 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.0000003385357559e-06, | |
| "count": 1, | |
| "self": 1.0000003385357559e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.05926490000274498, | |
| "count": 1, | |
| "self": 0.0012898000059067272, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.05797509999683825, | |
| "count": 1, | |
| "self": 0.05797509999683825 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |