| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.5703408718109131, |
| "min": 0.5684681534767151, |
| "max": 1.4670132398605347, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 17091.974609375, |
| "min": 16936.12890625, |
| "max": 44503.3125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989872.0, |
| "min": 29952.0, |
| "max": 989872.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989872.0, |
| "min": 29952.0, |
| "max": 989872.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.4391264319419861, |
| "min": -0.08845900744199753, |
| "max": 0.4391264319419861, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 117.24675750732422, |
| "min": -21.318620681762695, |
| "max": 117.24675750732422, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.060588207095861435, |
| "min": -0.005432200618088245, |
| "max": 0.28096574544906616, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 16.177051544189453, |
| "min": -1.41237211227417, |
| "max": 67.43177795410156, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06600444621536461, |
| "min": 0.06095544749405235, |
| "max": 0.07409931473464175, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9240622470151045, |
| "min": 0.5067585374649491, |
| "max": 1.0769645807061654, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014430946333295506, |
| "min": 0.0005125414362218846, |
| "max": 0.01625817823265618, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2020332486661371, |
| "min": 0.0066630386708845, |
| "max": 0.24387267348984273, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.3311761277357156e-06, |
| "min": 7.3311761277357156e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010263646578830002, |
| "min": 0.00010263646578830002, |
| "max": 0.0037576621474460004, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10244369285714286, |
| "min": 0.10244369285714286, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4342117, |
| "min": 1.3691136000000002, |
| "max": 2.6525540000000007, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025412491642857153, |
| "min": 0.00025412491642857153, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0035577488300000014, |
| "min": 0.0035577488300000014, |
| "max": 0.12527014460000002, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.0060813636519014835, |
| "min": 0.006006164941936731, |
| "max": 0.3740398585796356, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.08513908833265305, |
| "min": 0.08408630639314651, |
| "max": 2.618278980255127, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 401.51428571428573, |
| "min": 401.51428571428573, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28106.0, |
| "min": 15984.0, |
| "max": 33158.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.455585686649595, |
| "min": -1.0000000521540642, |
| "max": 1.521614898607802, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 101.89099806547165, |
| "min": -32.000001668930054, |
| "max": 108.76459883153439, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.455585686649595, |
| "min": -1.0000000521540642, |
| "max": 1.521614898607802, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 101.89099806547165, |
| "min": -32.000001668930054, |
| "max": 108.76459883153439, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.0252037998340841, |
| "min": 0.0252037998340841, |
| "max": 7.920950873754919, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.7642659883858869, |
| "min": 1.7546899187145755, |
| "max": 126.7352139800787, |
| "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": "1673377084", |
| "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
| "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": "1673379222" |
| }, |
| "total": 2137.282637745, |
| "count": 1, |
| "self": 0.42559533300027397, |
| "children": { |
| "run_training.setup": { |
| "total": 0.10954433799997787, |
| "count": 1, |
| "self": 0.10954433799997787 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2136.747498074, |
| "count": 1, |
| "self": 1.514010145002885, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 6.670010261000016, |
| "count": 1, |
| "self": 6.670010261000016 |
| }, |
| "TrainerController.advance": { |
| "total": 2128.4697951999974, |
| "count": 63726, |
| "self": 1.4533583410561732, |
| "children": { |
| "env_step": { |
| "total": 1423.4704000739755, |
| "count": 63726, |
| "self": 1308.1208945010549, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 114.45664726392329, |
| "count": 63726, |
| "self": 4.520313947959266, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 109.93633331596402, |
| "count": 62570, |
| "self": 36.63007661795882, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 73.3062566980052, |
| "count": 62570, |
| "self": 73.3062566980052 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8928583089973472, |
| "count": 63726, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2131.8008508900134, |
| "count": 63726, |
| "is_parallel": true, |
| "self": 932.7868211700104, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.001811122000162868, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006370169996898767, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0011741050004729914, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0011741050004729914 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04651548099991487, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005283049999889045, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00048262799987242033, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00048262799987242033 |
| }, |
| "communicator.exchange": { |
| "total": 0.043788471999960166, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.043788471999960166 |
| }, |
| "steps_from_proto": { |
| "total": 0.0017160760000933806, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004536320002443972, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012624439998489834, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012624439998489834 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1199.014029720003, |
| "count": 63725, |
| "is_parallel": true, |
| "self": 29.791249003150824, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.615163595904505, |
| "count": 63725, |
| "is_parallel": true, |
| "self": 23.615163595904505 |
| }, |
| "communicator.exchange": { |
| "total": 1047.384607814954, |
| "count": 63725, |
| "is_parallel": true, |
| "self": 1047.384607814954 |
| }, |
| "steps_from_proto": { |
| "total": 98.22300930599363, |
| "count": 63725, |
| "is_parallel": true, |
| "self": 23.534748617962578, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 74.68826068803105, |
| "count": 509800, |
| "is_parallel": true, |
| "self": 74.68826068803105 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 703.546036784966, |
| "count": 63726, |
| "self": 2.7176353519755594, |
| "children": { |
| "process_trajectory": { |
| "total": 153.1084956009936, |
| "count": 63726, |
| "self": 152.90925324599357, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.19924235500002396, |
| "count": 2, |
| "self": 0.19924235500002396 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 547.7199058319968, |
| "count": 454, |
| "self": 211.81871583999487, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 335.90118999200195, |
| "count": 22836, |
| "self": 335.90118999200195 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.150000212481245e-07, |
| "count": 1, |
| "self": 8.150000212481245e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09368165299974862, |
| "count": 1, |
| "self": 0.0014609879999625264, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.0922206649997861, |
| "count": 1, |
| "self": 0.0922206649997861 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
