| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.3502959609031677, |
| "min": 0.3502959609031677, |
| "max": 1.4698705673217773, |
| "count": 28 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 10525.693359375, |
| "min": 10525.693359375, |
| "max": 44589.9921875, |
| "count": 28 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 839989.0, |
| "min": 29923.0, |
| "max": 839989.0, |
| "count": 28 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 839989.0, |
| "min": 29923.0, |
| "max": 839989.0, |
| "count": 28 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.629786491394043, |
| "min": -0.09799198806285858, |
| "max": 0.629786491394043, |
| "count": 28 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 176.34022521972656, |
| "min": -23.616069793701172, |
| "max": 176.34022521972656, |
| "count": 28 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.004649701062589884, |
| "min": -0.013009719550609589, |
| "max": 0.26096516847610474, |
| "count": 28 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 1.301916241645813, |
| "min": -3.473595142364502, |
| "max": 62.89260482788086, |
| "count": 28 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06638622395569525, |
| "min": 0.06423629471100867, |
| "max": 0.0742484789061596, |
| "count": 28 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9294071353797335, |
| "min": 0.5012575005570523, |
| "max": 1.0661113334045855, |
| "count": 28 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01573695085660022, |
| "min": 0.0005568967800390506, |
| "max": 0.015971414667488328, |
| "count": 28 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2203173119924031, |
| "min": 0.007239658140507658, |
| "max": 0.2235998053448366, |
| "count": 28 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 0.0002175689131913238, |
| "min": 0.0002175689131913238, |
| "max": 0.0002984113862438238, |
| "count": 28 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.003045964784678533, |
| "min": 0.0020888797037067666, |
| "max": 0.004027256057581366, |
| "count": 28 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.1725229619047619, |
| "min": 0.1725229619047619, |
| "max": 0.19947046190476195, |
| "count": 28 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 2.4153214666666667, |
| "min": 1.3962932333333335, |
| "max": 2.8424186333333337, |
| "count": 28 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.007255043894285713, |
| "min": 0.007255043894285713, |
| "max": 0.009947099144285713, |
| "count": 28 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.10157061451999999, |
| "min": 0.06962969400999999, |
| "max": 0.13425762147, |
| "count": 28 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.013835138641297817, |
| "min": 0.01322467066347599, |
| "max": 0.3313908576965332, |
| "count": 28 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.1936919391155243, |
| "min": 0.18514539301395416, |
| "max": 2.3197360038757324, |
| "count": 28 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 313.3369565217391, |
| "min": 313.3369565217391, |
| "max": 992.875, |
| "count": 28 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28827.0, |
| "min": 16594.0, |
| "max": 32929.0, |
| "count": 28 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5561782439117846, |
| "min": -0.9310187993105501, |
| "max": 1.6087899799458683, |
| "count": 28 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 143.1683984398842, |
| "min": -30.246001705527306, |
| "max": 144.8747985586524, |
| "count": 28 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5561782439117846, |
| "min": -0.9310187993105501, |
| "max": 1.6087899799458683, |
| "count": 28 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 143.1683984398842, |
| "min": -30.246001705527306, |
| "max": 144.8747985586524, |
| "count": 28 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04438819246412174, |
| "min": 0.04438819246412174, |
| "max": 5.594401250867283, |
| "count": 28 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.0837137066992, |
| "min": 4.037327836878831, |
| "max": 95.1048212647438, |
| "count": 28 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 28 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 28 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1786768430", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "command_line_arguments": "/home/lagnesh/Projects/DeepRL/ml-agents/ml-agents/mlagents/trainers/learn.py /home/lagnesh/Projects/DeepRL/ml-agents/config/ppo/PyramidsRND.yaml --env=./Pyramids_env/Pyramids/Pyramids --run-id=PyramidsTraining1 --no-graphics --force", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1786771356" |
| }, |
| "total": 2795.8748361240005, |
| "count": 1, |
| "self": 3.5503616580008384, |
| "children": { |
| "run_training.setup": { |
| "total": 0.017944634999821574, |
| "count": 1, |
| "self": 0.017944634999821574 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2792.306529831, |
| "count": 1, |
| "self": 1.788223593083785, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.876147533999756, |
| "count": 1, |
| "self": 3.876147533999756 |
| }, |
| "TrainerController.advance": { |
| "total": 2785.636464730915, |
| "count": 54262, |
| "self": 1.963086632825707, |
| "children": { |
| "env_step": { |
| "total": 1893.3336433690815, |
| "count": 54262, |
| "self": 1582.394395377144, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 309.75291562593065, |
| "count": 54262, |
| "self": 7.058743866009536, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 302.6941717599211, |
| "count": 53113, |
| "self": 302.6941717599211 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.186332366006809, |
| "count": 54261, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2787.210104066988, |
| "count": 54261, |
| "is_parallel": true, |
| "self": 1328.0417568640319, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.001808707000236609, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0009546139999656589, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0008540930002709501, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0008540930002709501 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.03315804500016384, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00020833999997194041, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00021028000037404126, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00021028000037404126 |
| }, |
| "communicator.exchange": { |
| "total": 0.03215912499990736, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.03215912499990736 |
| }, |
| "steps_from_proto": { |
| "total": 0.0005802999999104941, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0001609020005162165, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0004193979993942776, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0004193979993942776 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1459.1683472029563, |
| "count": 54260, |
| "is_parallel": true, |
| "self": 20.472134827994523, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 16.000049496893098, |
| "count": 54260, |
| "is_parallel": true, |
| "self": 16.000049496893098 |
| }, |
| "communicator.exchange": { |
| "total": 1367.3548614210931, |
| "count": 54260, |
| "is_parallel": true, |
| "self": 1367.3548614210931 |
| }, |
| "steps_from_proto": { |
| "total": 55.34130145697554, |
| "count": 54260, |
| "is_parallel": true, |
| "self": 13.656972305909221, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 41.68432915106632, |
| "count": 434080, |
| "is_parallel": true, |
| "self": 41.68432915106632 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 890.3397347290079, |
| "count": 54261, |
| "self": 3.6681823540043297, |
| "children": { |
| "process_trajectory": { |
| "total": 145.49038223899788, |
| "count": 54261, |
| "self": 144.04397876999792, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 1.4464034689999608, |
| "count": 1, |
| "self": 1.4464034689999608 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 741.1811701360057, |
| "count": 385, |
| "self": 312.1338401250596, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 429.0473300109461, |
| "count": 19320, |
| "self": 429.0473300109461 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.7340007616439834e-06, |
| "count": 1, |
| "self": 1.7340007616439834e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 1.005692239000382, |
| "count": 1, |
| "self": 0.0028390030001901323, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 1.0028532360001918, |
| "count": 1, |
| "self": 1.0028532360001918 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
