| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.7713114619255066, |
| "min": 0.7413836121559143, |
| "max": 1.5325779914855957, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 23102.3203125, |
| "min": 22205.921875, |
| "max": 46492.28515625, |
| "count": 16 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 479947.0, |
| "min": 29952.0, |
| "max": 479947.0, |
| "count": 16 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 479947.0, |
| "min": 29952.0, |
| "max": 479947.0, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.053219493478536606, |
| "min": -0.12735284864902496, |
| "max": -0.04627450183033943, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -12.985556602478027, |
| "min": -30.18262481689453, |
| "max": -11.152154922485352, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.024932365864515305, |
| "min": -0.018909849226474762, |
| "max": 0.1254802793264389, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 6.083497047424316, |
| "min": -4.481634140014648, |
| "max": 30.240745544433594, |
| "count": 16 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06486455813316254, |
| "min": 0.06485790826671455, |
| "max": 0.07066501490327469, |
| "count": 16 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9081038138642755, |
| "min": 0.4763798093036534, |
| "max": 0.9893102086458456, |
| "count": 16 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.0036155476242183218, |
| "min": 0.00010375834745647652, |
| "max": 0.0036155476242183218, |
| "count": 16 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.0506176667390565, |
| "min": 0.0013488585169341948, |
| "max": 0.0506176667390565, |
| "count": 16 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 2.0755850224271423e-05, |
| "min": 2.0755850224271423e-05, |
| "max": 0.00029030126037577137, |
| "count": 16 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0002905819031397999, |
| "min": 0.0002905819031397999, |
| "max": 0.0026049806316732, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10691858571428574, |
| "min": 0.10691858571428574, |
| "max": 0.19676708571428575, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4968602000000004, |
| "min": 1.3773696000000002, |
| "max": 2.1701246, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0007011667128571428, |
| "min": 0.0007011667128571428, |
| "max": 0.00967703186285714, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00981633398, |
| "min": 0.00981633398, |
| "max": 0.08685584731999998, |
| "count": 16 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.018735188990831375, |
| "min": 0.018735188990831375, |
| "max": 0.2695947289466858, |
| "count": 16 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.26229265332221985, |
| "min": 0.26229265332221985, |
| "max": 1.8871631622314453, |
| "count": 16 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 865.3823529411765, |
| "min": 865.3823529411765, |
| "max": 999.0, |
| "count": 16 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29423.0, |
| "min": 15984.0, |
| "max": 32696.0, |
| "count": 16 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": -0.3953588675050175, |
| "min": -1.0000000521540642, |
| "max": -0.3953588675050175, |
| "count": 16 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": -13.442201495170593, |
| "min": -31.996801659464836, |
| "max": -13.442201495170593, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": -0.3953588675050175, |
| "min": -1.0000000521540642, |
| "max": -0.3953588675050175, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": -13.442201495170593, |
| "min": -31.996801659464836, |
| "max": -13.442201495170593, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.16947927908040583, |
| "min": 0.16947927908040583, |
| "max": 5.419171486515552, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 5.762295488733798, |
| "min": 5.762295488733798, |
| "max": 86.70674378424883, |
| "count": 16 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 16 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 16 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1667375682", |
| "python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \n[GCC 7.5.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 0001 --no-graphics", |
| "mlagents_version": "0.29.0.dev0", |
| "mlagents_envs_version": "0.29.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.8.1+cu102", |
| "numpy_version": "1.21.6", |
| "end_time_seconds": "1667376730" |
| }, |
| "total": 1048.1399435140002, |
| "count": 1, |
| "self": 0.49644337900008395, |
| "children": { |
| "run_training.setup": { |
| "total": 0.050323142000024745, |
| "count": 1, |
| "self": 0.050323142000024745 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1047.593176993, |
| "count": 1, |
| "self": 0.7114934100011396, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 11.506129040000133, |
| "count": 1, |
| "self": 11.506129040000133 |
| }, |
| "TrainerController.advance": { |
| "total": 1035.2754225919991, |
| "count": 31506, |
| "self": 0.8017189389681789, |
| "children": { |
| "env_step": { |
| "total": 660.8455849730271, |
| "count": 31506, |
| "self": 604.7117530640226, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 55.75326815901121, |
| "count": 31506, |
| "self": 2.4064152030530295, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 53.346852955958184, |
| "count": 31317, |
| "self": 18.18563022897206, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 35.161222726986125, |
| "count": 31317, |
| "self": 35.161222726986125 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.38056374999337095, |
| "count": 31506, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1045.2095230399962, |
| "count": 31506, |
| "is_parallel": true, |
| "self": 494.36141488600424, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.008157683000035831, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0033196780002526793, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.004838004999783152, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.004838004999783152 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04479758299999048, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005308479999257543, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00043541200011532055, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00043541200011532055 |
| }, |
| "communicator.exchange": { |
| "total": 0.042109202999881745, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.042109202999881745 |
| }, |
| "steps_from_proto": { |
| "total": 0.0017221200000676617, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004500519999055541, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012720680001621076, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012720680001621076 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 550.8481081539919, |
| "count": 31505, |
| "is_parallel": true, |
| "self": 14.623722969002984, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 12.017403656984015, |
| "count": 31505, |
| "is_parallel": true, |
| "self": 12.017403656984015 |
| }, |
| "communicator.exchange": { |
| "total": 469.1472572789892, |
| "count": 31505, |
| "is_parallel": true, |
| "self": 469.1472572789892 |
| }, |
| "steps_from_proto": { |
| "total": 55.059724249015744, |
| "count": 31505, |
| "is_parallel": true, |
| "self": 12.348540299028173, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 42.71118394998757, |
| "count": 252040, |
| "is_parallel": true, |
| "self": 42.71118394998757 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 373.6281186800038, |
| "count": 31506, |
| "self": 1.1878231370062622, |
| "children": { |
| "process_trajectory": { |
| "total": 83.86899326099774, |
| "count": 31506, |
| "self": 83.76374448499791, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10524877599982574, |
| "count": 1, |
| "self": 0.10524877599982574 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 288.5713022819998, |
| "count": 206, |
| "self": 115.45540353299862, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 173.1158987490012, |
| "count": 11421, |
| "self": 173.1158987490012 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.1229999472561758e-06, |
| "count": 1, |
| "self": 1.1229999472561758e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10013082799969197, |
| "count": 1, |
| "self": 0.0016978039998321037, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09843302399985987, |
| "count": 1, |
| "self": 0.09843302399985987 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
