| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.2894322872161865, |
| "min": 0.2816106379032135, |
| "max": 0.3480154275894165, |
| "count": 27 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 8682.96875, |
| "min": 6999.18505859375, |
| "max": 10384.7802734375, |
| "count": 27 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 232.51162790697674, |
| "min": 209.11764705882354, |
| "max": 308.48979591836735, |
| "count": 27 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29994.0, |
| "min": 17266.0, |
| "max": 32873.0, |
| "count": 27 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2399911.0, |
| "min": 1619908.0, |
| "max": 2399911.0, |
| "count": 27 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2399911.0, |
| "min": 1619908.0, |
| "max": 2399911.0, |
| "count": 27 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.775632381439209, |
| "min": 0.640011727809906, |
| "max": 0.8253579139709473, |
| "count": 27 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 230.36282348632812, |
| "min": 136.5261688232422, |
| "max": 253.38189697265625, |
| "count": 27 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.0022314651869237423, |
| "min": -0.021407801657915115, |
| "max": 0.03117687813937664, |
| "count": 27 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -0.6627451777458191, |
| "min": -6.336709022521973, |
| "max": 9.259532928466797, |
| "count": 27 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.751982929863671, |
| "min": 1.6506754907266217, |
| "max": 1.7907956114215573, |
| "count": 27 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 226.00579795241356, |
| "min": 128.73399847745895, |
| "max": 245.33899876475334, |
| "count": 27 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.751982929863671, |
| "min": 1.6506754907266217, |
| "max": 1.7907956114215573, |
| "count": 27 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 226.00579795241356, |
| "min": 128.73399847745895, |
| "max": 245.33899876475334, |
| "count": 27 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.030091278991831626, |
| "min": 0.029591189495382694, |
| "max": 0.048203936919147664, |
| "count": 27 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.8817749899462797, |
| "min": 2.7676298303413205, |
| "max": 4.907326885942894, |
| "count": 27 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.04867695555246125, |
| "min": 0.04449985193665877, |
| "max": 0.0523126974627043, |
| "count": 27 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.38941564441969, |
| "min": 0.19394374480665041, |
| "max": 0.38941564441969, |
| "count": 27 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01636384917461934, |
| "min": 0.013374935272925844, |
| "max": 0.01636384917461934, |
| "count": 27 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.13091079339695472, |
| "min": 0.05664326411594327, |
| "max": 0.13091079339695472, |
| "count": 27 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.9055837398385495e-06, |
| "min": 1.9055837398385495e-06, |
| "max": 9.87013483495729e-05, |
| "count": 27 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 1.5244669918708396e-05, |
| "min": 1.5244669918708396e-05, |
| "max": 0.0007646479201175416, |
| "count": 27 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10063516145833333, |
| "min": 0.10063516145833333, |
| "max": 0.13290042708333333, |
| "count": 27 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 0.8050812916666666, |
| "min": 0.5316017083333333, |
| "max": 1.0548824583333334, |
| "count": 27 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 7.345262968750026e-05, |
| "min": 7.345262968750026e-05, |
| "max": 0.0032967526656250004, |
| "count": 27 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0005876210375000021, |
| "min": 0.0005876210375000021, |
| "max": 0.0255427575875, |
| "count": 27 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.012674783356487751, |
| "min": 0.01223958283662796, |
| "max": 0.015598742291331291, |
| "count": 27 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.10139826685190201, |
| "min": 0.062394969165325165, |
| "max": 0.12225722521543503, |
| "count": 27 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 27 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 27 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1788963807", |
| "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", |
| "command_line_arguments": "/content/mlagents-venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --resume", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.2.2+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1788965935" |
| }, |
| "total": 2128.3313611070007, |
| "count": 1, |
| "self": 0.4851569950005796, |
| "children": { |
| "run_training.setup": { |
| "total": 0.018255455999678816, |
| "count": 1, |
| "self": 0.018255455999678816 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2127.8279486560004, |
| "count": 1, |
| "self": 1.3241436350490403, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.7344684770014283, |
| "count": 1, |
| "self": 1.7344684770014283 |
| }, |
| "TrainerController.advance": { |
| "total": 2124.6835644499497, |
| "count": 52681, |
| "self": 1.3159501759128034, |
| "children": { |
| "env_step": { |
| "total": 1717.8678067681467, |
| "count": 52681, |
| "self": 1589.1483397418197, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 127.92158403502617, |
| "count": 52681, |
| "self": 4.025039495658348, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 123.89654453936782, |
| "count": 50053, |
| "self": 123.89654453936782 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7978829913008667, |
| "count": 52681, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2123.0883227349805, |
| "count": 52681, |
| "is_parallel": true, |
| "self": 635.169838795835, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002127575000486104, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006809879996581003, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014465870008280035, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014465870008280035 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05590457700054685, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005653939988405909, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004589260006468976, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004589260006468976 |
| }, |
| "communicator.exchange": { |
| "total": 0.05313486700106296, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05313486700106296 |
| }, |
| "steps_from_proto": { |
| "total": 0.001745389999996405, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00038869100353622343, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013566989964601817, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013566989964601817 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1487.9184839391455, |
| "count": 52680, |
| "is_parallel": true, |
| "self": 27.787577147777483, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 19.66753624812918, |
| "count": 52680, |
| "is_parallel": true, |
| "self": 19.66753624812918 |
| }, |
| "communicator.exchange": { |
| "total": 1349.4675085100498, |
| "count": 52680, |
| "is_parallel": true, |
| "self": 1349.4675085100498 |
| }, |
| "steps_from_proto": { |
| "total": 90.99586203318904, |
| "count": 52680, |
| "is_parallel": true, |
| "self": 19.789881249433165, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 71.20598078375588, |
| "count": 421440, |
| "is_parallel": true, |
| "self": 71.20598078375588 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 405.4998075058902, |
| "count": 52681, |
| "self": 2.531578156071191, |
| "children": { |
| "process_trajectory": { |
| "total": 95.11150788183477, |
| "count": 52681, |
| "self": 94.9995362088357, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.11197167299906141, |
| "count": 1, |
| "self": 0.11197167299906141 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 307.85672146798424, |
| "count": 192, |
| "self": 200.099346059058, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 107.75737540892624, |
| "count": 9219, |
| "self": 107.75737540892624 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.3280005077831447e-06, |
| "count": 1, |
| "self": 1.3280005077831447e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08577076599976863, |
| "count": 1, |
| "self": 0.0015646559986635111, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08420611000110512, |
| "count": 1, |
| "self": 0.08420611000110512 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
