| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.15211382508277893, |
| "min": 0.14719398319721222, |
| "max": 1.4341914653778076, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 4629.1279296875, |
| "min": 4418.1748046875, |
| "max": 43507.6328125, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999983.0, |
| "min": 29889.0, |
| "max": 2999983.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999983.0, |
| "min": 29889.0, |
| "max": 2999983.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.8182088136672974, |
| "min": -0.0989677682518959, |
| "max": 0.8213458061218262, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 245.462646484375, |
| "min": -23.950199127197266, |
| "max": 247.36431884765625, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.008533334359526634, |
| "min": -0.04254058003425598, |
| "max": 0.27854689955711365, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 2.560000419616699, |
| "min": -11.230712890625, |
| "max": 66.01561737060547, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06947986950521641, |
| "min": 0.06498012068775659, |
| "max": 0.07431449605009947, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9727181730730297, |
| "min": 0.6503406154801992, |
| "max": 1.0770408910009828, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01643688442530039, |
| "min": 9.780023517921777e-05, |
| "max": 0.017112599614645455, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.23011638195420547, |
| "min": 0.0010758025869713954, |
| "max": 0.25668899421968183, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.4431923761119025e-06, |
| "min": 1.4431923761119025e-06, |
| "max": 0.0002984275560797037, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.0204693265566636e-05, |
| "min": 2.0204693265566636e-05, |
| "max": 0.0038476809174397665, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10048103095238095, |
| "min": 0.10048103095238095, |
| "max": 0.1994758518518519, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4067344333333334, |
| "min": 1.4067344333333334, |
| "max": 2.7825602333333332, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.805499214285707e-05, |
| "min": 5.805499214285707e-05, |
| "max": 0.0099476376, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.000812769889999999, |
| "min": 0.000812769889999999, |
| "max": 0.12827776731, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.0055196331813931465, |
| "min": 0.005187662318348885, |
| "max": 0.3690737783908844, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.0772748664021492, |
| "min": 0.07314175367355347, |
| "max": 3.3216640949249268, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 228.53333333333333, |
| "min": 225.0514705882353, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30852.0, |
| "min": 16432.0, |
| "max": 33784.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7418310909359545, |
| "min": -1.0000000521540642, |
| "max": 1.7615359884500503, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 235.14719727635384, |
| "min": -32.000001668930054, |
| "max": 239.39259764552116, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7418310909359545, |
| "min": -1.0000000521540642, |
| "max": 1.7615359884500503, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 235.14719727635384, |
| "min": -32.000001668930054, |
| "max": 239.39259764552116, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.012937411113913793, |
| "min": 0.012937411113913793, |
| "max": 7.070920380599358, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.746550500378362, |
| "min": 1.6136930264692637, |
| "max": 120.2056464701891, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1777193313", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "command_line_arguments": "/home/zhaoji/miniconda3/envs/HFDeepRL/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
| "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": "1777198566" |
| }, |
| "total": 5252.951924169, |
| "count": 1, |
| "self": 0.47733541400066315, |
| "children": { |
| "run_training.setup": { |
| "total": 0.043003597000279115, |
| "count": 1, |
| "self": 0.043003597000279115 |
| }, |
| "TrainerController.start_learning": { |
| "total": 5252.4315851579995, |
| "count": 1, |
| "self": 3.557694449938026, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 5.713611182000022, |
| "count": 1, |
| "self": 5.713611182000022 |
| }, |
| "TrainerController.advance": { |
| "total": 5242.98914531406, |
| "count": 194864, |
| "self": 3.040190601712311, |
| "children": { |
| "env_step": { |
| "total": 3201.705803798721, |
| "count": 194864, |
| "self": 2543.1791005634977, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 656.0563206784818, |
| "count": 194864, |
| "self": 9.670798630772879, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 646.385522047709, |
| "count": 187572, |
| "self": 646.385522047709 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.4703825567412423, |
| "count": 194864, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 5244.766403304152, |
| "count": 194864, |
| "is_parallel": true, |
| "self": 2939.8344455970055, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002184551000027568, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0010431969985802425, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0011413540014473256, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0011413540014473256 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.02166267200027505, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003421200008233427, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00015923799946904182, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00015923799946904182 |
| }, |
| "communicator.exchange": { |
| "total": 0.020651261000239174, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.020651261000239174 |
| }, |
| "steps_from_proto": { |
| "total": 0.0005100529997434933, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00010862199906114256, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0004014310006823507, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0004014310006823507 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 2304.9319577071465, |
| "count": 194863, |
| "is_parallel": true, |
| "self": 32.2349189900242, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 24.481125296973005, |
| "count": 194863, |
| "is_parallel": true, |
| "self": 24.481125296973005 |
| }, |
| "communicator.exchange": { |
| "total": 2153.392425668082, |
| "count": 194863, |
| "is_parallel": true, |
| "self": 2153.392425668082 |
| }, |
| "steps_from_proto": { |
| "total": 94.8234877520672, |
| "count": 194863, |
| "is_parallel": true, |
| "self": 22.475704745164876, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 72.34778300690232, |
| "count": 1558904, |
| "is_parallel": true, |
| "self": 72.34778300690232 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 2038.2431509136268, |
| "count": 194864, |
| "self": 7.055243498468371, |
| "children": { |
| "process_trajectory": { |
| "total": 339.23116035514704, |
| "count": 194864, |
| "self": 338.3145479411478, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.9166124139992462, |
| "count": 6, |
| "self": 0.9166124139992462 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1691.9567470600114, |
| "count": 1394, |
| "self": 680.1054422367388, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 1011.8513048232726, |
| "count": 68391, |
| "self": 1011.8513048232726 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 6.410009518731385e-07, |
| "count": 1, |
| "self": 6.410009518731385e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.17113357100060966, |
| "count": 1, |
| "self": 0.02329794900106208, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.14783562199954758, |
| "count": 1, |
| "self": 0.14783562199954758 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
