| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.189856618642807, |
| "min": 0.1817089468240738, |
| "max": 0.3481859266757965, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 5726.07568359375, |
| "min": 5480.341796875, |
| "max": 10272.8779296875, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 249.94573643410854, |
| "min": 230.5703125, |
| "max": 364.6666666666667, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 32243.0, |
| "min": 17353.0, |
| "max": 32243.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1979995.0, |
| "min": 1019988.0, |
| "max": 1979995.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1979995.0, |
| "min": 1019988.0, |
| "max": 1979995.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7693508267402649, |
| "min": 0.5625669956207275, |
| "max": 0.8056074380874634, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 230.8052520751953, |
| "min": 103.35254669189453, |
| "max": 238.45980834960938, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.004943689797073603, |
| "min": -0.004943689797073603, |
| "max": 0.04152600094676018, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -1.4831069707870483, |
| "min": -1.4831069707870483, |
| "max": 11.83491039276123, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.735264048911631, |
| "min": 1.5612444244785073, |
| "max": 1.7675039833784103, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 222.11379826068878, |
| "min": 96.64699840545654, |
| "max": 228.18799858540297, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.735264048911631, |
| "min": 1.5612444244785073, |
| "max": 1.7675039833784103, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 222.11379826068878, |
| "min": 96.64699840545654, |
| "max": 228.18799858540297, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.02587083513401467, |
| "min": 0.024559607545597828, |
| "max": 0.05238411585616385, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.3114668971538777, |
| "min": 2.692943104368169, |
| "max": 4.350430508609861, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06605385297734756, |
| "min": 0.06359199066323021, |
| "max": 0.07284611712836957, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9247539416828658, |
| "min": 0.5931617736607543, |
| "max": 1.040361449122429, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01609122662089898, |
| "min": 0.01255998326559973, |
| "max": 0.016918032216317415, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.22527717269258574, |
| "min": 0.11886353706301866, |
| "max": 0.23685245102844382, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 5.261755388971429e-06, |
| "min": 5.261755388971429e-06, |
| "max": 0.00014841648386118886, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 7.36645754456e-05, |
| "min": 7.36645754456e-05, |
| "max": 0.0020265499244836002, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10175388571428572, |
| "min": 0.10175388571428572, |
| "max": 0.14947214444444443, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4245544, |
| "min": 1.3452492999999999, |
| "max": 2.1336950999999997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00018521318285714286, |
| "min": 0.00018521318285714286, |
| "max": 0.00495226723, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00259298456, |
| "min": 0.00259298456, |
| "max": 0.06762408835999999, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.009953402914106846, |
| "min": 0.009953402914106846, |
| "max": 0.015164068900048733, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.139347642660141, |
| "min": 0.13647662103176117, |
| "max": 0.2004043012857437, |
| "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": "1693046857", |
| "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --resume", |
| "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": "1693049565" |
| }, |
| "total": 2707.949965885, |
| "count": 1, |
| "self": 0.4775602929998968, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0623524739999084, |
| "count": 1, |
| "self": 0.0623524739999084 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2707.410053118, |
| "count": 1, |
| "self": 1.6329233869714699, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 5.2107627870000215, |
| "count": 1, |
| "self": 5.2107627870000215 |
| }, |
| "TrainerController.advance": { |
| "total": 2700.4612155600284, |
| "count": 65365, |
| "self": 1.561065242126915, |
| "children": { |
| "env_step": { |
| "total": 2008.4881389168577, |
| "count": 65365, |
| "self": 1891.3168267420342, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 116.24314791791585, |
| "count": 65365, |
| "self": 4.9299677619242175, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 111.31318015599163, |
| "count": 62555, |
| "self": 111.31318015599163 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.9281642569076212, |
| "count": 65365, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2700.989232571038, |
| "count": 65365, |
| "is_parallel": true, |
| "self": 936.2675088729279, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002749479999692994, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006598020004275895, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0020896779992654047, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0020896779992654047 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05014101799997661, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005669600000146602, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005053139998381084, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005053139998381084 |
| }, |
| "communicator.exchange": { |
| "total": 0.04710479200002737, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04710479200002737 |
| }, |
| "steps_from_proto": { |
| "total": 0.0019639520000964694, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000376612000309251, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015873399997872184, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015873399997872184 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1764.72172369811, |
| "count": 65364, |
| "is_parallel": true, |
| "self": 35.592770060198745, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.265593657970385, |
| "count": 65364, |
| "is_parallel": true, |
| "self": 23.265593657970385 |
| }, |
| "communicator.exchange": { |
| "total": 1593.6019322240054, |
| "count": 65364, |
| "is_parallel": true, |
| "self": 1593.6019322240054 |
| }, |
| "steps_from_proto": { |
| "total": 112.26142775593553, |
| "count": 65364, |
| "is_parallel": true, |
| "self": 22.869903264721415, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 89.39152449121411, |
| "count": 522912, |
| "is_parallel": true, |
| "self": 89.39152449121411 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 690.4120114010439, |
| "count": 65365, |
| "self": 3.0458836080670153, |
| "children": { |
| "process_trajectory": { |
| "total": 120.1345750539781, |
| "count": 65365, |
| "self": 119.91976739297888, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.2148076609992131, |
| "count": 2, |
| "self": 0.2148076609992131 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 567.2315527389987, |
| "count": 471, |
| "self": 371.40067953005564, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 195.8308732089431, |
| "count": 22692, |
| "self": 195.8308732089431 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.820005288929678e-07, |
| "count": 1, |
| "self": 9.820005288929678e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10515040199970827, |
| "count": 1, |
| "self": 0.0016279530000247178, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10352244899968355, |
| "count": 1, |
| "self": 0.10352244899968355 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
