| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.21000109612941742, |
| "min": 0.20282530784606934, |
| "max": 1.4987908601760864, |
| "count": 50 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 6464.673828125, |
| "min": 5945.21533203125, |
| "max": 47961.30859375, |
| "count": 50 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1499937.0, |
| "min": 29965.0, |
| "max": 1499937.0, |
| "count": 50 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1499937.0, |
| "min": 29965.0, |
| "max": 1499937.0, |
| "count": 50 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7420340180397034, |
| "min": -0.17377686500549316, |
| "max": 0.7843450903892517, |
| "count": 50 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 123.91968536376953, |
| "min": -20.85322380065918, |
| "max": 139.03561401367188, |
| "count": 50 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.012078857980668545, |
| "min": -0.019199013710021973, |
| "max": 0.2037448137998581, |
| "count": 50 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 2.017169237136841, |
| "min": -3.0718421936035156, |
| "max": 24.24563217163086, |
| "count": 50 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06815258119584171, |
| "min": 0.06520804375645192, |
| "max": 0.07585374099660049, |
| "count": 50 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9541361367417839, |
| "min": 0.4942462240869483, |
| "max": 1.0322288755132296, |
| "count": 50 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015690698891164635, |
| "min": 0.0005699708628393532, |
| "max": 0.01702291942171391, |
| "count": 50 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2196697844763049, |
| "min": 0.0062696794912328845, |
| "max": 0.23832087190399476, |
| "count": 50 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 4.887884736728569e-06, |
| "min": 4.887884736728569e-06, |
| "max": 0.0004946118106014476, |
| "count": 50 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 6.843038631419997e-05, |
| "min": 6.843038631419997e-05, |
| "max": 0.0056679849330697335, |
| "count": 50 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10097755714285717, |
| "min": 0.10097755714285717, |
| "max": 0.19892236190476195, |
| "count": 50 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4136858000000003, |
| "min": 1.3367888, |
| "max": 2.5335969333333335, |
| "count": 50 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00010765795857142852, |
| "min": 0.00010765795857142852, |
| "max": 0.009892343954285714, |
| "count": 50 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0015072114199999992, |
| "min": 0.0015072114199999992, |
| "max": 0.11338633363999998, |
| "count": 50 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.008972442708909512, |
| "min": 0.008972442708909512, |
| "max": 0.3135761618614197, |
| "count": 50 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.125614196062088, |
| "min": 0.125614196062088, |
| "max": 2.195033073425293, |
| "count": 50 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 241.43650793650792, |
| "min": 221.6390977443609, |
| "max": 999.0, |
| "count": 50 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30421.0, |
| "min": 15984.0, |
| "max": 32212.0, |
| "count": 50 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7268110842458786, |
| "min": -0.9999833926558495, |
| "max": 1.7783608810794085, |
| "count": 50 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 217.5781966149807, |
| "min": -30.991601705551147, |
| "max": 236.52199718356133, |
| "count": 50 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7268110842458786, |
| "min": -0.9999833926558495, |
| "max": 1.7783608810794085, |
| "count": 50 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 217.5781966149807, |
| "min": -30.991601705551147, |
| "max": 236.52199718356133, |
| "count": 50 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.022587337922376473, |
| "min": 0.02104095551924941, |
| "max": 4.860745341206591, |
| "count": 50 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.8460045782194356, |
| "min": 2.7697720539363218, |
| "max": 116.65788818895817, |
| "count": 50 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 50 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 50 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1674231325", |
| "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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_3 --no-graphics", |
| "mlagents_version": "0.29.0.dev0", |
| "mlagents_envs_version": "0.29.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.8.1+cu102", |
| "numpy_version": "1.21.6", |
| "end_time_seconds": "1674234826" |
| }, |
| "total": 3501.122817852, |
| "count": 1, |
| "self": 0.5005281789999572, |
| "children": { |
| "run_training.setup": { |
| "total": 0.10767898599999626, |
| "count": 1, |
| "self": 0.10767898599999626 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3500.514610687, |
| "count": 1, |
| "self": 2.2532774779651845, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 10.534003471999995, |
| "count": 1, |
| "self": 10.534003471999995 |
| }, |
| "TrainerController.advance": { |
| "total": 3487.6434426440346, |
| "count": 97001, |
| "self": 2.3407994440258335, |
| "children": { |
| "env_step": { |
| "total": 2485.6283189029996, |
| "count": 97001, |
| "self": 2308.430676666088, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 175.7803666209516, |
| "count": 97001, |
| "self": 7.038472659936815, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 168.7418939610148, |
| "count": 93882, |
| "self": 56.8360830440385, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 111.9058109169763, |
| "count": 93882, |
| "self": 111.9058109169763 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.4172756159600794, |
| "count": 97001, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3493.2578676929543, |
| "count": 97001, |
| "is_parallel": true, |
| "self": 1353.4987849779236, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.005190994000031424, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0028228090001789496, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002368184999852474, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.002368184999852474 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.0638987070000212, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005594220000375572, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.000514979999991283, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000514979999991283 |
| }, |
| "communicator.exchange": { |
| "total": 0.0599889229999917, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0599889229999917 |
| }, |
| "steps_from_proto": { |
| "total": 0.0028353820000006635, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0015007220000597954, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013346599999408681, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013346599999408681 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 2139.7590827150307, |
| "count": 97000, |
| "is_parallel": true, |
| "self": 45.53715751911068, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 35.538468998951544, |
| "count": 97000, |
| "is_parallel": true, |
| "self": 35.538468998951544 |
| }, |
| "communicator.exchange": { |
| "total": 1913.2542705909866, |
| "count": 97000, |
| "is_parallel": true, |
| "self": 1913.2542705909866 |
| }, |
| "steps_from_proto": { |
| "total": 145.42918560598156, |
| "count": 97000, |
| "is_parallel": true, |
| "self": 35.18899929605499, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 110.24018630992657, |
| "count": 776000, |
| "is_parallel": true, |
| "self": 110.24018630992657 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 999.674324297009, |
| "count": 97001, |
| "self": 4.681280775965433, |
| "children": { |
| "process_trajectory": { |
| "total": 203.42490704703954, |
| "count": 97001, |
| "self": 202.97044644403962, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.45446060299991586, |
| "count": 5, |
| "self": 0.45446060299991586 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 791.568136474004, |
| "count": 648, |
| "self": 299.4080673410608, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 492.16006913294314, |
| "count": 34269, |
| "self": 492.16006913294314 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 7.769999683659989e-07, |
| "count": 1, |
| "self": 7.769999683659989e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08388631600018925, |
| "count": 1, |
| "self": 0.0013932040005784074, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08249311199961085, |
| "count": 1, |
| "self": 0.08249311199961085 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
