| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.18083599209785461, |
| "min": 0.1753084659576416, |
| "max": 1.5017955303192139, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 5436.6533203125, |
| "min": 5249.01318359375, |
| "max": 45558.46875, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999984.0, |
| "min": 29952.0, |
| "max": 2999984.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999984.0, |
| "min": 29952.0, |
| "max": 2999984.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6283080577850342, |
| "min": -0.1075344979763031, |
| "max": 0.710053563117981, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 182.20933532714844, |
| "min": -25.808279037475586, |
| "max": 206.62559509277344, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.013113018125295639, |
| "min": -0.045015666633844376, |
| "max": 0.2258395403623581, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 3.8027751445770264, |
| "min": -12.244261741638184, |
| "max": 53.52397155761719, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06543375354577168, |
| "min": 0.06533164033850986, |
| "max": 0.07680259531834888, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9160725496408034, |
| "min": 0.49085674155436604, |
| "max": 1.1051700265767672, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014990372544811439, |
| "min": 5.436072959934471e-05, |
| "max": 0.016239398962560308, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.20986521562736016, |
| "min": 0.0006523287551921365, |
| "max": 0.23327813882982204, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.4828137914761926e-06, |
| "min": 1.4828137914761926e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.0759393080666696e-05, |
| "min": 2.0759393080666696e-05, |
| "max": 0.0036750671749776658, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10049423809523808, |
| "min": 0.10049423809523808, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4069193333333332, |
| "min": 1.3897045333333333, |
| "max": 2.6774543, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.937438571428578e-05, |
| "min": 5.937438571428578e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008312414000000009, |
| "min": 0.0008312414000000009, |
| "max": 0.12251973110000003, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.002524538431316614, |
| "min": 0.002524538431316614, |
| "max": 0.31970641016960144, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.03534353896975517, |
| "min": 0.03534353896975517, |
| "max": 2.2379448413848877, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 295.1509433962264, |
| "min": 257.070796460177, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31286.0, |
| "min": 15984.0, |
| "max": 33219.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.64823017079594, |
| "min": -1.0000000521540642, |
| "max": 1.7397192809403987, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 174.71239810436964, |
| "min": -32.000001668930054, |
| "max": 198.32799802720547, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.64823017079594, |
| "min": -1.0000000521540642, |
| "max": 1.7397192809403987, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 174.71239810436964, |
| "min": -32.000001668930054, |
| "max": 198.32799802720547, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.007778382844130733, |
| "min": 0.007355977590729405, |
| "max": 6.568125128746033, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 0.8245085814778577, |
| "min": 0.7868847954487137, |
| "max": 105.09000205993652, |
| "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": "1771817183", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn /content/ml-agents/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": "1771824291" |
| }, |
| "total": 7107.776239903, |
| "count": 1, |
| "self": 0.5264534219995767, |
| "children": { |
| "run_training.setup": { |
| "total": 0.01900760100033949, |
| "count": 1, |
| "self": 0.01900760100033949 |
| }, |
| "TrainerController.start_learning": { |
| "total": 7107.23077888, |
| "count": 1, |
| "self": 4.64455457547956, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.0930156269996587, |
| "count": 1, |
| "self": 2.0930156269996587 |
| }, |
| "TrainerController.advance": { |
| "total": 7100.415967424522, |
| "count": 193200, |
| "self": 4.922077457418709, |
| "children": { |
| "env_step": { |
| "total": 5076.800874323141, |
| "count": 193200, |
| "self": 4588.924436536091, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 485.0967085192651, |
| "count": 193200, |
| "self": 14.74740999003734, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 470.3492985292278, |
| "count": 187557, |
| "self": 470.3492985292278 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.7797292677851146, |
| "count": 193200, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 7088.043072083577, |
| "count": 193200, |
| "is_parallel": true, |
| "self": 2874.006202681652, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0019067630000790814, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006636380003328668, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012431249997462146, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012431249997462146 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04939114300032088, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006225080005606287, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005004570002711262, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005004570002711262 |
| }, |
| "communicator.exchange": { |
| "total": 0.04644637999990664, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04644637999990664 |
| }, |
| "steps_from_proto": { |
| "total": 0.0018217979995824862, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00039283499972952995, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014289629998529563, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014289629998529563 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 4214.036869401924, |
| "count": 193199, |
| "is_parallel": true, |
| "self": 106.85728159333121, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 75.00446174797798, |
| "count": 193199, |
| "is_parallel": true, |
| "self": 75.00446174797798 |
| }, |
| "communicator.exchange": { |
| "total": 3688.72128981442, |
| "count": 193199, |
| "is_parallel": true, |
| "self": 3688.72128981442 |
| }, |
| "steps_from_proto": { |
| "total": 343.45383624619535, |
| "count": 193199, |
| "is_parallel": true, |
| "self": 72.49425999826599, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 270.95957624792936, |
| "count": 1545592, |
| "is_parallel": true, |
| "self": 270.95957624792936 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 2018.693015643962, |
| "count": 193200, |
| "self": 8.837307861845147, |
| "children": { |
| "process_trajectory": { |
| "total": 397.01164160717144, |
| "count": 193200, |
| "self": 396.39577367117, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.6158679360014503, |
| "count": 6, |
| "self": 0.6158679360014503 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1612.8440661749455, |
| "count": 1374, |
| "self": 886.0230709779626, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 726.820995196983, |
| "count": 68463, |
| "self": 726.820995196983 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0159983503399417e-06, |
| "count": 1, |
| "self": 1.0159983503399417e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.07724023700029647, |
| "count": 1, |
| "self": 0.0010557690002315212, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.07618446800006495, |
| "count": 1, |
| "self": 0.07618446800006495 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
