| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.31358128786087036, |
| "min": 0.31358128786087036, |
| "max": 1.4539014101028442, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 9402.4208984375, |
| "min": 9402.4208984375, |
| "max": 44105.5546875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989974.0, |
| "min": 29953.0, |
| "max": 989974.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989974.0, |
| "min": 29953.0, |
| "max": 989974.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7181461453437805, |
| "min": -0.1340368688106537, |
| "max": 0.7181461453437805, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 208.26239013671875, |
| "min": -32.302886962890625, |
| "max": 208.26239013671875, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.09090358763933182, |
| "min": -0.002665511565282941, |
| "max": 0.38728198409080505, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 26.362041473388672, |
| "min": -0.7783293724060059, |
| "max": 92.17311096191406, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06659276291664594, |
| "min": 0.06459357717985233, |
| "max": 0.07275264047703243, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9322986808330431, |
| "min": 0.5637706339411986, |
| "max": 1.0610107503832527, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.017363992994672395, |
| "min": 0.0010747919660771133, |
| "max": 0.0176823972364045, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.24309590192541353, |
| "min": 0.011822711626848247, |
| "max": 0.26132612709725256, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.6177617464928555e-06, |
| "min": 7.6177617464928555e-06, |
| "max": 0.0002948542892152375, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010664866445089998, |
| "min": 0.00010664866445089998, |
| "max": 0.0036331402889532996, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10253922142857144, |
| "min": 0.10253922142857144, |
| "max": 0.19828476250000002, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4355491000000002, |
| "min": 1.4355491000000002, |
| "max": 2.6110467, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00026366822071428566, |
| "min": 0.00026366822071428566, |
| "max": 0.009828647773750001, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0036913550899999995, |
| "min": 0.0036913550899999995, |
| "max": 0.12112356533000002, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.01170145720243454, |
| "min": 0.011364221572875977, |
| "max": 0.46374616026878357, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.16382040083408356, |
| "min": 0.15909910202026367, |
| "max": 3.7099692821502686, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 258.2368421052632, |
| "min": 258.2368421052632, |
| "max": 994.3548387096774, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29439.0, |
| "min": 16368.0, |
| "max": 32565.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7242122667661883, |
| "min": -0.9271576282652941, |
| "max": 1.7365344685727153, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 196.56019841134548, |
| "min": -30.596201732754707, |
| "max": 201.43799835443497, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7242122667661883, |
| "min": -0.9271576282652941, |
| "max": 1.7365344685727153, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 196.56019841134548, |
| "min": -30.596201732754707, |
| "max": 201.43799835443497, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.031107573971798717, |
| "min": 0.031107573971798717, |
| "max": 9.475205338286127, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.5462634327850537, |
| "min": 3.4790745124046225, |
| "max": 161.07849075086415, |
| "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": "1793720675", |
| "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", |
| "command_line_arguments": "./.venv-mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --torch-device=cuda:0", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.2.2+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1793723532" |
| }, |
| "total": 2856.585274717014, |
| "count": 1, |
| "self": 0.47321838507195935, |
| "children": { |
| "run_training.setup": { |
| "total": 0.020167832961305976, |
| "count": 1, |
| "self": 0.020167832961305976 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2856.0918884989806, |
| "count": 1, |
| "self": 1.7123010059585795, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 6.516610554012004, |
| "count": 1, |
| "self": 6.516610554012004 |
| }, |
| "TrainerController.advance": { |
| "total": 2847.760597955028, |
| "count": 64302, |
| "self": 1.7578528755693696, |
| "children": { |
| "env_step": { |
| "total": 1800.4117568892543, |
| "count": 64302, |
| "self": 1429.1347496459493, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 370.20822148106527, |
| "count": 64302, |
| "self": 6.6543933093198575, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 363.5538281717454, |
| "count": 62565, |
| "self": 363.5538281717454 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.0687857622397132, |
| "count": 64302, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2852.023492543143, |
| "count": 64302, |
| "is_parallel": true, |
| "self": 1533.3473185344483, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002168135019019246, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007176109356805682, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014505240833386779, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014505240833386779 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.0496182200149633, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00039510708302259445, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00021310296142473817, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00021310296142473817 |
| }, |
| "communicator.exchange": { |
| "total": 0.04813429497880861, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04813429497880861 |
| }, |
| "steps_from_proto": { |
| "total": 0.0008757149917073548, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00020160386338829994, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0006741111283190548, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0006741111283190548 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1318.676174008695, |
| "count": 64301, |
| "is_parallel": true, |
| "self": 18.354288078204263, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 14.496296016790438, |
| "count": 64301, |
| "is_parallel": true, |
| "self": 14.496296016790438 |
| }, |
| "communicator.exchange": { |
| "total": 1233.6586510364432, |
| "count": 64301, |
| "is_parallel": true, |
| "self": 1233.6586510364432 |
| }, |
| "steps_from_proto": { |
| "total": 52.16693887725705, |
| "count": 64301, |
| "is_parallel": true, |
| "self": 13.15001504716929, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 39.01692383008776, |
| "count": 514408, |
| "is_parallel": true, |
| "self": 39.01692383008776 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1045.5909881902044, |
| "count": 64302, |
| "self": 3.232551448745653, |
| "children": { |
| "process_trajectory": { |
| "total": 147.281706314825, |
| "count": 64302, |
| "self": 147.03345442481805, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.2482518900069408, |
| "count": 2, |
| "self": 0.2482518900069408 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 895.0767304266337, |
| "count": 455, |
| "self": 349.03322012443095, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 546.0435103022028, |
| "count": 22791, |
| "self": 546.0435103022028 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.1999509297311306e-06, |
| "count": 1, |
| "self": 1.1999509297311306e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10237778403097764, |
| "count": 1, |
| "self": 0.0010425170185044408, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.1013352670124732, |
| "count": 1, |
| "self": 0.1013352670124732 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
