| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.5948482155799866, |
| "min": 0.5882039666175842, |
| "max": 1.4243783950805664, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 17950.140625, |
| "min": 17533.18359375, |
| "max": 43209.94140625, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989948.0, |
| "min": 29952.0, |
| "max": 989948.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989948.0, |
| "min": 29952.0, |
| "max": 989948.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.3088169991970062, |
| "min": -0.12626424431800842, |
| "max": 0.3572804927825928, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 80.29241943359375, |
| "min": -30.303417205810547, |
| "max": 94.67932891845703, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.015330884605646133, |
| "min": 0.0004837263550143689, |
| "max": 0.2976463735103607, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 3.986030101776123, |
| "min": 0.12141531705856323, |
| "max": 70.54219055175781, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.0676849256276971, |
| "min": 0.06672542845363683, |
| "max": 0.07313829511606078, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9475889587877593, |
| "min": 0.4769172992084935, |
| "max": 1.0822500859229716, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.011846537781291197, |
| "min": 0.00012236330646575244, |
| "max": 0.012664181497193758, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.16585152893807675, |
| "min": 0.0015907229840547816, |
| "max": 0.18754871489427924, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.344033266307141e-06, |
| "min": 7.344033266307141e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010281646572829997, |
| "min": 0.00010281646572829997, |
| "max": 0.0033819926726691993, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.1024479785714286, |
| "min": 0.1024479785714286, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4342717000000003, |
| "min": 1.3691136000000002, |
| "max": 2.5273307999999997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002545530592857143, |
| "min": 0.0002545530592857143, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0035637428299999997, |
| "min": 0.0035637428299999997, |
| "max": 0.11276034691999998, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.012461100704967976, |
| "min": 0.012461100704967976, |
| "max": 0.35382720828056335, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.1744554042816162, |
| "min": 0.1744554042816162, |
| "max": 2.476790428161621, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 564.2982456140351, |
| "min": 498.36206896551727, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 32165.0, |
| "min": 15984.0, |
| "max": 32561.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.1576464028496827, |
| "min": -1.0000000521540642, |
| "max": 1.289121284225925, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 64.82819855958223, |
| "min": -32.000001668930054, |
| "max": 78.63639833778143, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.1576464028496827, |
| "min": -1.0000000521540642, |
| "max": 1.289121284225925, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 64.82819855958223, |
| "min": -32.000001668930054, |
| "max": 78.63639833778143, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.07090864898249752, |
| "min": 0.06554012912685019, |
| "max": 7.030538386665285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.9708843430198613, |
| "min": 3.7357873602304608, |
| "max": 112.48861418664455, |
| "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": "1681153036", |
| "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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-v1 --no-graphics", |
| "mlagents_version": "0.31.0.dev0", |
| "mlagents_envs_version": "0.31.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.11.0+cu102", |
| "numpy_version": "1.21.2", |
| "end_time_seconds": "1681155046" |
| }, |
| "total": 2010.2554323159998, |
| "count": 1, |
| "self": 0.7856397209993702, |
| "children": { |
| "run_training.setup": { |
| "total": 0.11082381699998223, |
| "count": 1, |
| "self": 0.11082381699998223 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2009.3589687780004, |
| "count": 1, |
| "self": 1.2486640189290483, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 4.770761165000295, |
| "count": 1, |
| "self": 4.770761165000295 |
| }, |
| "TrainerController.advance": { |
| "total": 2003.1885895670712, |
| "count": 63246, |
| "self": 1.3982830790168919, |
| "children": { |
| "env_step": { |
| "total": 1402.3319653839594, |
| "count": 63246, |
| "self": 1299.8738540119566, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 101.6548734099888, |
| "count": 63246, |
| "self": 4.469341740988057, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 97.18553166900074, |
| "count": 62550, |
| "self": 97.18553166900074 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8032379620140091, |
| "count": 63246, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2004.668425206049, |
| "count": 63246, |
| "is_parallel": true, |
| "self": 808.1095741530826, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.001998802000343858, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007888750001256994, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012099270002181584, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012099270002181584 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.07682180399979188, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005357400000320922, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00045355900010690675, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00045355900010690675 |
| }, |
| "communicator.exchange": { |
| "total": 0.0742779059996792, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0742779059996792 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015545989999736776, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003650389994618308, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0011895600005118467, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0011895600005118467 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1196.5588510529665, |
| "count": 63245, |
| "is_parallel": true, |
| "self": 31.42347325080209, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 22.39034784701289, |
| "count": 63245, |
| "is_parallel": true, |
| "self": 22.39034784701289 |
| }, |
| "communicator.exchange": { |
| "total": 1052.2300749069882, |
| "count": 63245, |
| "is_parallel": true, |
| "self": 1052.2300749069882 |
| }, |
| "steps_from_proto": { |
| "total": 90.5149550481633, |
| "count": 63245, |
| "is_parallel": true, |
| "self": 18.94819589114195, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 71.56675915702135, |
| "count": 505960, |
| "is_parallel": true, |
| "self": 71.56675915702135 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 599.4583411040949, |
| "count": 63246, |
| "self": 2.2828734990530393, |
| "children": { |
| "process_trajectory": { |
| "total": 99.94875587303568, |
| "count": 63246, |
| "self": 99.63883660803594, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.3099192649997349, |
| "count": 2, |
| "self": 0.3099192649997349 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 497.22671173200615, |
| "count": 430, |
| "self": 317.6877947599892, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 179.53891697201698, |
| "count": 22863, |
| "self": 179.53891697201698 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.4659999578725547e-06, |
| "count": 1, |
| "self": 1.4659999578725547e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.15095256099994003, |
| "count": 1, |
| "self": 0.002016295999965223, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.1489362649999748, |
| "count": 1, |
| "self": 0.1489362649999748 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
