| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.3680855631828308, |
| "min": 0.35760974884033203, |
| "max": 1.4710440635681152, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 10971.89453125, |
| "min": 10796.953125, |
| "max": 44625.59375, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989971.0, |
| "min": 29952.0, |
| "max": 989971.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989971.0, |
| "min": 29952.0, |
| "max": 989971.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.5916125774383545, |
| "min": -0.11956167221069336, |
| "max": 0.628807783126831, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 163.87667846679688, |
| "min": -28.336116790771484, |
| "max": 176.8218231201172, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -9.931435488397256e-05, |
| "min": -0.0491173081099987, |
| "max": 0.3131968080997467, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -0.027510076761245728, |
| "min": -13.900197982788086, |
| "max": 75.167236328125, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06911843978672377, |
| "min": 0.06341371592134237, |
| "max": 0.07463349583063873, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9676581570141328, |
| "min": 0.4921823382202333, |
| "max": 1.0520527274130989, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014397754568822812, |
| "min": 0.0005648293115770901, |
| "max": 0.015972497850140953, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.20156856396351938, |
| "min": 0.007342781050502171, |
| "max": 0.22395190081328573, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.691647436150003e-06, |
| "min": 7.691647436150003e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010768306410610005, |
| "min": 0.00010768306410610005, |
| "max": 0.0035071430309524, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10256385000000001, |
| "min": 0.10256385000000001, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4358939000000002, |
| "min": 1.3691136000000002, |
| "max": 2.5690476000000007, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002661286150000001, |
| "min": 0.0002661286150000001, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0037258006100000015, |
| "min": 0.0037258006100000015, |
| "max": 0.11692785524, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.013178681023418903, |
| "min": 0.012945860624313354, |
| "max": 0.43729692697525024, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.1845015287399292, |
| "min": 0.18317164480686188, |
| "max": 3.0610785484313965, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 327.1511627906977, |
| "min": 303.019801980198, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28135.0, |
| "min": 15984.0, |
| "max": 32958.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6010776269085267, |
| "min": -1.0000000521540642, |
| "max": 1.695322903028379, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 136.09159828722477, |
| "min": -32.000001668930054, |
| "max": 167.39319813996553, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6010776269085267, |
| "min": -1.0000000521540642, |
| "max": 1.695322903028379, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 136.09159828722477, |
| "min": -32.000001668930054, |
| "max": 167.39319813996553, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04445960371042876, |
| "min": 0.04114266927526932, |
| "max": 9.519774168729782, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.7790663153864443, |
| "min": 3.7790663153864443, |
| "max": 152.3163866996765, |
| "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": "1674392048", |
| "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1674394127" |
| }, |
| "total": 2078.486793776, |
| "count": 1, |
| "self": 0.4379099329999008, |
| "children": { |
| "run_training.setup": { |
| "total": 0.10050329200021224, |
| "count": 1, |
| "self": 0.10050329200021224 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2077.948380551, |
| "count": 1, |
| "self": 1.2741841079850929, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 6.037845322999601, |
| "count": 1, |
| "self": 6.037845322999601 |
| }, |
| "TrainerController.advance": { |
| "total": 2070.5289886430155, |
| "count": 63947, |
| "self": 1.271330257106456, |
| "children": { |
| "env_step": { |
| "total": 1425.6939646029232, |
| "count": 63947, |
| "self": 1319.0152575400589, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 105.8829090999634, |
| "count": 63947, |
| "self": 4.384102037000957, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 101.49880706296244, |
| "count": 62572, |
| "self": 33.784254267920915, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 67.71455279504153, |
| "count": 62572, |
| "self": 67.71455279504153 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.795797962900906, |
| "count": 63947, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2073.171742680872, |
| "count": 63947, |
| "is_parallel": true, |
| "self": 854.5375784518237, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0020438299998204457, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007796269992468297, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001264203000573616, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001264203000573616 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05627572699995653, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005220150005698088, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004675620002672076, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004675620002672076 |
| }, |
| "communicator.exchange": { |
| "total": 0.05363959099940985, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05363959099940985 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016465589997096686, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00040870800057746237, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012378509991322062, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012378509991322062 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1218.634164229048, |
| "count": 63946, |
| "is_parallel": true, |
| "self": 27.560490296054013, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.222023684935266, |
| "count": 63946, |
| "is_parallel": true, |
| "self": 23.222023684935266 |
| }, |
| "communicator.exchange": { |
| "total": 1065.345101970086, |
| "count": 63946, |
| "is_parallel": true, |
| "self": 1065.345101970086 |
| }, |
| "steps_from_proto": { |
| "total": 102.5065482779728, |
| "count": 63946, |
| "is_parallel": true, |
| "self": 22.70552653964296, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 79.80102173832984, |
| "count": 511568, |
| "is_parallel": true, |
| "self": 79.80102173832984 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 643.5636937829859, |
| "count": 63947, |
| "self": 2.339736057050686, |
| "children": { |
| "process_trajectory": { |
| "total": 147.56514329292713, |
| "count": 63947, |
| "self": 147.37875930092832, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.1863839919988095, |
| "count": 2, |
| "self": 0.1863839919988095 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 493.65881443300805, |
| "count": 448, |
| "self": 184.5995740759954, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 309.05924035701264, |
| "count": 22812, |
| "self": 309.05924035701264 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.071999577106908e-06, |
| "count": 1, |
| "self": 1.071999577106908e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.1073614050001197, |
| "count": 1, |
| "self": 0.0015955420003592735, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10576586299976043, |
| "count": 1, |
| "self": 0.10576586299976043 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
