| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.5779170393943787, | |
| "min": 0.5779170393943787, | |
| "max": 1.442322850227356, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 17411.484375, | |
| "min": 17411.484375, | |
| "max": 43754.3046875, | |
| "count": 20 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 599929.0, | |
| "min": 29952.0, | |
| "max": 599929.0, | |
| "count": 20 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 599929.0, | |
| "min": 29952.0, | |
| "max": 599929.0, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.18661844730377197, | |
| "min": -0.11054674535989761, | |
| "max": 0.18661844730377197, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 47.587703704833984, | |
| "min": -26.641765594482422, | |
| "max": 47.587703704833984, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.016434624791145325, | |
| "min": 0.016434624791145325, | |
| "max": 0.35958778858184814, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 4.190829277038574, | |
| "min": 4.190829277038574, | |
| "max": 85.22230529785156, | |
| "count": 20 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06422510723905743, | |
| "min": 0.06422510723905743, | |
| "max": 0.0736837605644214, | |
| "count": 20 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.8991515013468041, | |
| "min": 0.5157863239509498, | |
| "max": 1.0369858075282536, | |
| "count": 20 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.011843530881174876, | |
| "min": 0.00031659532405810796, | |
| "max": 0.011843530881174876, | |
| "count": 20 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.16580943233644826, | |
| "min": 0.004432334536813512, | |
| "max": 0.16580943233644826, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.993061621392858e-06, | |
| "min": 7.993061621392858e-06, | |
| "max": 0.0002919177169798095, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00011190286269950001, | |
| "min": 0.00011190286269950001, | |
| "max": 0.0032213517262161665, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10266432142857143, | |
| "min": 0.10266432142857143, | |
| "max": 0.1973059047619048, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4373005, | |
| "min": 1.3811413333333336, | |
| "max": 2.3737838333333334, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.00027616571071428575, | |
| "min": 0.00027616571071428575, | |
| "max": 0.009730859885714286, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0038663199500000005, | |
| "min": 0.0038663199500000005, | |
| "max": 0.10740100495, | |
| "count": 20 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.0190260112285614, | |
| "min": 0.0190260112285614, | |
| "max": 0.4770812690258026, | |
| "count": 20 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.2663641571998596, | |
| "min": 0.2663641571998596, | |
| "max": 3.339568853378296, | |
| "count": 20 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 642.1111111111111, | |
| "min": 642.1111111111111, | |
| "max": 999.0, | |
| "count": 20 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 28895.0, | |
| "min": 15984.0, | |
| "max": 33080.0, | |
| "count": 20 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 0.8393434482100217, | |
| "min": -1.0000000521540642, | |
| "max": 0.8393434482100217, | |
| "count": 20 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 38.609798617661, | |
| "min": -29.633201643824577, | |
| "max": 38.609798617661, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 0.8393434482100217, | |
| "min": -1.0000000521540642, | |
| "max": 0.8393434482100217, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 38.609798617661, | |
| "min": -29.633201643824577, | |
| "max": 38.609798617661, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.12539062814080945, | |
| "min": 0.12539062814080945, | |
| "max": 10.89297050703317, | |
| "count": 20 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 5.767968894477235, | |
| "min": 5.767968894477235, | |
| "max": 174.2875281125307, | |
| "count": 20 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 20 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 20 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1680166888", | |
| "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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 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": "1680168061" | |
| }, | |
| "total": 1173.0982683469997, | |
| "count": 1, | |
| "self": 0.9909899219996987, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.11148743800004013, | |
| "count": 1, | |
| "self": 0.11148743800004013 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 1171.995790987, | |
| "count": 1, | |
| "self": 0.794952939011182, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 6.782739793000019, | |
| "count": 1, | |
| "self": 6.782739793000019 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 1164.1038740839886, | |
| "count": 38026, | |
| "self": 0.8418140149165083, | |
| "children": { | |
| "env_step": { | |
| "total": 791.7397666659617, | |
| "count": 38026, | |
| "self": 726.5317094160187, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 64.7211457540111, | |
| "count": 38026, | |
| "self": 2.8574207559549905, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 61.863724998056114, | |
| "count": 37568, | |
| "self": 61.863724998056114 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.48691149593196315, | |
| "count": 38026, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 1169.0864541419392, | |
| "count": 38026, | |
| "is_parallel": true, | |
| "self": 510.77933398292316, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0018568139998933475, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006395450000127312, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012172689998806163, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012172689998806163 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.0762697529999059, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005124630001773767, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00048429999969812343, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00048429999969812343 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.0735128920000534, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0735128920000534 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0017600979999770061, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00036175599962007254, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0013983420003569336, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0013983420003569336 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 658.307120159016, | |
| "count": 38025, | |
| "is_parallel": true, | |
| "self": 18.40534018176413, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 13.86856746406238, | |
| "count": 38025, | |
| "is_parallel": true, | |
| "self": 13.86856746406238 | |
| }, | |
| "communicator.exchange": { | |
| "total": 570.3618061491584, | |
| "count": 38025, | |
| "is_parallel": true, | |
| "self": 570.3618061491584 | |
| }, | |
| "steps_from_proto": { | |
| "total": 55.6714063640311, | |
| "count": 38025, | |
| "is_parallel": true, | |
| "self": 11.89616714106387, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 43.77523922296723, | |
| "count": 304200, | |
| "is_parallel": true, | |
| "self": 43.77523922296723 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 371.5222934031103, | |
| "count": 38026, | |
| "self": 1.4451327371893967, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 71.76933010892208, | |
| "count": 38026, | |
| "self": 71.66158862192151, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.10774148700056685, | |
| "count": 1, | |
| "self": 0.10774148700056685 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 298.30783055699885, | |
| "count": 264, | |
| "self": 189.86364553996555, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 108.4441850170333, | |
| "count": 13671, | |
| "self": 108.4441850170333 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.3910002962802537e-06, | |
| "count": 1, | |
| "self": 1.3910002962802537e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.3142227799999091, | |
| "count": 1, | |
| "self": 0.0018257340007039602, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.31239704599920515, | |
| "count": 1, | |
| "self": 0.31239704599920515 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |