| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.05442899465560913, |
| "min": 0.05242244154214859, |
| "max": 1.3705583810806274, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 1630.2572021484375, |
| "min": 1570.156982421875, |
| "max": 41577.2578125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989968.0, |
| "min": 29952.0, |
| "max": 989968.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989968.0, |
| "min": 29952.0, |
| "max": 989968.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.08903234452009201, |
| "min": -0.19419239461421967, |
| "max": -0.06629885733127594, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -21.45679473876953, |
| "min": -46.023597717285156, |
| "max": -15.911725044250488, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 1.8214921951293945, |
| "min": 0.5243939161300659, |
| "max": 1.9033710956573486, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 438.9796142578125, |
| "min": 124.28135681152344, |
| "max": 456.8090515136719, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.0661242809109142, |
| "min": 0.06374541939982933, |
| "max": 0.07348706931681415, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9257399327527988, |
| "min": 0.49297044531528533, |
| "max": 1.0518959731128361, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.012577719092250054, |
| "min": 0.006498080227699513, |
| "max": 0.015008765833921264, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.17608806729150075, |
| "min": 0.0456589584831107, |
| "max": 0.2101227216748977, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.445368946814284e-06, |
| "min": 7.445368946814284e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010423516525539997, |
| "min": 0.00010423516525539997, |
| "max": 0.0035071262309579994, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10248175714285714, |
| "min": 0.10248175714285714, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4347446, |
| "min": 1.3691136000000002, |
| "max": 2.569042, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025792753857142853, |
| "min": 0.00025792753857142853, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0036109855399999997, |
| "min": 0.0036109855399999997, |
| "max": 0.11692729580000001, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 1.7528276443481445, |
| "min": 0.7230812311172485, |
| "max": 1.852443814277649, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 24.539587020874023, |
| "min": 5.061568737030029, |
| "max": 26.377004623413086, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 983.8064516129032, |
| "min": 940.65625, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30498.0, |
| "min": 15984.0, |
| "max": 32196.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": -0.8553355365030227, |
| "min": -1.0000000521540642, |
| "max": -0.5864727756742275, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": -26.515401631593704, |
| "min": -32.000001668930054, |
| "max": -16.000000834465027, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": -0.8553355365030227, |
| "min": -1.0000000521540642, |
| "max": -0.5864727756742275, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": -26.515401631593704, |
| "min": -32.000001668930054, |
| "max": -16.000000834465027, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 17.47547754741484, |
| "min": 8.902866526506841, |
| "max": 19.275136475916952, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 541.7398039698601, |
| "min": 182.65632048249245, |
| "max": 616.8043672293425, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1683948199", |
| "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
| "mlagents_version": "0.31.0.dev0", |
| "mlagents_envs_version": "0.31.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.11.0+cu102", |
| "numpy_version": "1.21.2", |
| "end_time_seconds": "1683950222" |
| }, |
| "total": 2023.2703064890002, |
| "count": 1, |
| "self": 0.4897319130000142, |
| "children": { |
| "run_training.setup": { |
| "total": 0.03951113999983136, |
| "count": 1, |
| "self": 0.03951113999983136 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2022.7410634360003, |
| "count": 1, |
| "self": 1.2682850310879985, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.8666184040002918, |
| "count": 1, |
| "self": 3.8666184040002918 |
| }, |
| "TrainerController.advance": { |
| "total": 2017.506221589912, |
| "count": 63088, |
| "self": 1.266177702870209, |
| "children": { |
| "env_step": { |
| "total": 1375.1449792800668, |
| "count": 63088, |
| "self": 1270.238804433127, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 104.15725104301418, |
| "count": 63088, |
| "self": 4.671053054906679, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 99.4861979881075, |
| "count": 62570, |
| "self": 99.4861979881075 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7489238039256634, |
| "count": 63088, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2018.2663062048541, |
| "count": 63088, |
| "is_parallel": true, |
| "self": 855.0315835768715, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0019216620003135176, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000595396999415243, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013262650008982746, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013262650008982746 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.049162566999712, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005438389998744242, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004680259999076952, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004680259999076952 |
| }, |
| "communicator.exchange": { |
| "total": 0.04631025800017596, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04631025800017596 |
| }, |
| "steps_from_proto": { |
| "total": 0.0018404439997539157, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00037927299990769825, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014611709998462175, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014611709998462175 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1163.2347226279826, |
| "count": 63087, |
| "is_parallel": true, |
| "self": 31.210451911947075, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 22.538860369974827, |
| "count": 63087, |
| "is_parallel": true, |
| "self": 22.538860369974827 |
| }, |
| "communicator.exchange": { |
| "total": 1012.3771904499936, |
| "count": 63087, |
| "is_parallel": true, |
| "self": 1012.3771904499936 |
| }, |
| "steps_from_proto": { |
| "total": 97.10821989606711, |
| "count": 63087, |
| "is_parallel": true, |
| "self": 19.61620053789329, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 77.49201935817382, |
| "count": 504696, |
| "is_parallel": true, |
| "self": 77.49201935817382 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 641.095064606975, |
| "count": 63088, |
| "self": 2.423816819091826, |
| "children": { |
| "process_trajectory": { |
| "total": 104.8063269808822, |
| "count": 63088, |
| "self": 104.49901272788293, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.3073142529992765, |
| "count": 2, |
| "self": 0.3073142529992765 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 533.864920807001, |
| "count": 443, |
| "self": 344.94355836099294, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 188.92136244600806, |
| "count": 22947, |
| "self": 188.92136244600806 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.050001270021312e-07, |
| "count": 1, |
| "self": 8.050001270021312e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.0999376059999122, |
| "count": 1, |
| "self": 0.0013802109997413936, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.0985573950001708, |
| "count": 1, |
| "self": 0.0985573950001708 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
