| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.4145159423351288, | |
| "min": 0.39505794644355774, | |
| "max": 1.4615728855133057, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 12481.904296875, | |
| "min": 11769.56640625, | |
| "max": 44338.2734375, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989956.0, | |
| "min": 29952.0, | |
| "max": 989956.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989956.0, | |
| "min": 29952.0, | |
| "max": 989956.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.46841374039649963, | |
| "min": -0.0892973467707634, | |
| "max": 0.518684983253479, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 128.81378173828125, | |
| "min": -21.60995864868164, | |
| "max": 143.6757354736328, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.013625477440655231, | |
| "min": -0.011528671719133854, | |
| "max": 0.2523898780345917, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 3.747006416320801, | |
| "min": -2.9974546432495117, | |
| "max": 59.81639862060547, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.0702229450592616, | |
| "min": 0.06459398017336969, | |
| "max": 0.07259833485853966, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9831212308296624, | |
| "min": 0.49098295995887986, | |
| "max": 1.0589703651494347, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.01816930671477513, | |
| "min": 0.001104623610743517, | |
| "max": 0.01816930671477513, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.25437029400685185, | |
| "min": 0.00773236527520462, | |
| "max": 0.25437029400685185, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.2983904243785715e-06, | |
| "min": 7.2983904243785715e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.0001021774659413, | |
| "min": 0.0001021774659413, | |
| "max": 0.0035079236306922003, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10243276428571428, | |
| "min": 0.10243276428571428, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4340587, | |
| "min": 1.3691136000000002, | |
| "max": 2.5724506000000003, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0002530331521428572, | |
| "min": 0.0002530331521428572, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0035424641300000003, | |
| "min": 0.0035424641300000003, | |
| "max": 0.11695384921999999, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.007899971678853035, | |
| "min": 0.007571976166218519, | |
| "max": 0.378082275390625, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.11059960722923279, | |
| "min": 0.11059960722923279, | |
| "max": 2.646575927734375, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 379.1518987341772, | |
| "min": 362.9886363636364, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 29953.0, | |
| "min": 15984.0, | |
| "max": 32732.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.5195518747160706, | |
| "min": -1.0000000521540642, | |
| "max": 1.5460772554136135, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 120.04459810256958, | |
| "min": -32.000001668930054, | |
| "max": 136.054798476398, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.5195518747160706, | |
| "min": -1.0000000521540642, | |
| "max": 1.5460772554136135, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 120.04459810256958, | |
| "min": -32.000001668930054, | |
| "max": 136.054798476398, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.031000774188698094, | |
| "min": 0.031000774188698094, | |
| "max": 7.615291692316532, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 2.4490611609071493, | |
| "min": 2.3408643143775407, | |
| "max": 121.84466707706451, | |
| "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": "1700124838", | |
| "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", | |
| "mlagents_version": "1.1.0.dev0", | |
| "mlagents_envs_version": "1.1.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.1.0+cu118", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1700127100" | |
| }, | |
| "total": 2262.334005138, | |
| "count": 1, | |
| "self": 0.47608266500037644, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0646938320001027, | |
| "count": 1, | |
| "self": 0.0646938320001027 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2261.7932286409996, | |
| "count": 1, | |
| "self": 1.4105596180024804, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 4.273941358999991, | |
| "count": 1, | |
| "self": 4.273941358999991 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2256.033334690996, | |
| "count": 63888, | |
| "self": 1.5242778130132137, | |
| "children": { | |
| "env_step": { | |
| "total": 1604.6665857659316, | |
| "count": 63888, | |
| "self": 1470.0345779679171, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 133.75330558391147, | |
| "count": 63888, | |
| "self": 4.765079610875318, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 128.98822597303615, | |
| "count": 62569, | |
| "self": 128.98822597303615 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.8787022141029865, | |
| "count": 63888, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2257.0660295159328, | |
| "count": 63888, | |
| "is_parallel": true, | |
| "self": 906.4497667690061, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0024804439999570604, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006597030001103121, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0018207409998467483, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0018207409998467483 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.04637395700001434, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005705550001948723, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00045611699988512555, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00045611699988512555 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04365029099994899, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04365029099994899 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0016969939999853523, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004314080001677212, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001265585999817631, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001265585999817631 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1350.6162627469266, | |
| "count": 63887, | |
| "is_parallel": true, | |
| "self": 34.32827445189946, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 24.082458527934932, | |
| "count": 63887, | |
| "is_parallel": true, | |
| "self": 24.082458527934932 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1194.5589413890073, | |
| "count": 63887, | |
| "is_parallel": true, | |
| "self": 1194.5589413890073 | |
| }, | |
| "steps_from_proto": { | |
| "total": 97.64658837808497, | |
| "count": 63887, | |
| "is_parallel": true, | |
| "self": 19.80372555715212, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 77.84286282093285, | |
| "count": 511096, | |
| "is_parallel": true, | |
| "self": 77.84286282093285 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 649.8424711120513, | |
| "count": 63888, | |
| "self": 2.6872450780413146, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 122.76566957600858, | |
| "count": 63888, | |
| "self": 122.55870364200769, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.20696593400089114, | |
| "count": 2, | |
| "self": 0.20696593400089114 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 524.3895564580014, | |
| "count": 451, | |
| "self": 316.9074659940193, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 207.4820904639821, | |
| "count": 22821, | |
| "self": 207.4820904639821 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 9.840005077421665e-07, | |
| "count": 1, | |
| "self": 9.840005077421665e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.07539198900030897, | |
| "count": 1, | |
| "self": 0.0013340610003069742, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.074057928000002, | |
| "count": 1, | |
| "self": 0.074057928000002 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |