| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.8341489434242249, |
| "min": 0.8341489434242249, |
| "max": 1.437943458557129, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 25024.46875, |
| "min": 25024.46875, |
| "max": 43621.453125, |
| "count": 16 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 479915.0, |
| "min": 29952.0, |
| "max": 479915.0, |
| "count": 16 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 479915.0, |
| "min": 29952.0, |
| "max": 479915.0, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.09666759520769119, |
| "min": -0.08215032517910004, |
| "max": 0.25575530529022217, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 24.07023048400879, |
| "min": -19.71607780456543, |
| "max": 60.614009857177734, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.025496231392025948, |
| "min": 0.02393612451851368, |
| "max": 0.438051700592041, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 6.348561763763428, |
| "min": 5.912222862243652, |
| "max": 103.81825256347656, |
| "count": 16 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06605156904760832, |
| "min": 0.06594023411348938, |
| "max": 0.07174256868408216, |
| "count": 16 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9247219666665165, |
| "min": 0.48902487655417143, |
| "max": 1.049707814323483, |
| "count": 16 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.007429880501692095, |
| "min": 0.0005903526648019358, |
| "max": 0.007429880501692095, |
| "count": 16 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.10401832702368932, |
| "min": 0.006493879312821293, |
| "max": 0.10984065934826502, |
| "count": 16 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 2.0946350160771434e-05, |
| "min": 2.0946350160771434e-05, |
| "max": 0.00029030126037577137, |
| "count": 16 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0002932489022508001, |
| "min": 0.0002932489022508001, |
| "max": 0.0028505426498192, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10698208571428572, |
| "min": 0.10698208571428572, |
| "max": 0.19676708571428575, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4977492000000001, |
| "min": 1.3773696000000002, |
| "max": 2.1708157999999997, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0007075103628571432, |
| "min": 0.0007075103628571432, |
| "max": 0.00967703186285714, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.009905145080000004, |
| "min": 0.009905145080000004, |
| "max": 0.09504306191999999, |
| "count": 16 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.021310335025191307, |
| "min": 0.021310335025191307, |
| "max": 0.399213045835495, |
| "count": 16 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.2983447015285492, |
| "min": 0.2983447015285492, |
| "max": 2.7944912910461426, |
| "count": 16 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 740.9285714285714, |
| "min": 740.9285714285714, |
| "max": 999.0, |
| "count": 16 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31119.0, |
| "min": 15984.0, |
| "max": 32536.0, |
| "count": 16 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 0.2587809179510389, |
| "min": -1.0000000521540642, |
| "max": 0.28630948598895756, |
| "count": 16 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 10.868798553943634, |
| "min": -30.53460170328617, |
| "max": 12.024998411536217, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 0.2587809179510389, |
| "min": -1.0000000521540642, |
| "max": 0.28630948598895756, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 10.868798553943634, |
| "min": -30.53460170328617, |
| "max": 12.024998411536217, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.16385969481918783, |
| "min": 0.16385969481918783, |
| "max": 7.7894810270518064, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 6.882107182405889, |
| "min": 6.706708388694096, |
| "max": 124.6316964328289, |
| "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": "1671645980", |
| "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=./trained-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": "1671646938" |
| }, |
| "total": 957.7829837869999, |
| "count": 1, |
| "self": 0.39308084499998586, |
| "children": { |
| "run_training.setup": { |
| "total": 0.10263272899987896, |
| "count": 1, |
| "self": 0.10263272899987896 |
| }, |
| "TrainerController.start_learning": { |
| "total": 957.287270213, |
| "count": 1, |
| "self": 0.5625604209719768, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 7.173057020999977, |
| "count": 1, |
| "self": 7.173057020999977 |
| }, |
| "TrainerController.advance": { |
| "total": 949.458850721028, |
| "count": 31602, |
| "self": 0.6291353279768828, |
| "children": { |
| "env_step": { |
| "total": 622.0962961320436, |
| "count": 31602, |
| "self": 570.3855794150318, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 51.34949984903437, |
| "count": 31602, |
| "self": 2.1962398760676933, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 49.15325997296668, |
| "count": 31306, |
| "self": 16.600076438946417, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 32.55318353402026, |
| "count": 31306, |
| "self": 32.55318353402026 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.3612168679774186, |
| "count": 31602, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 955.1745560310005, |
| "count": 31602, |
| "is_parallel": true, |
| "self": 433.83427060497934, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.005371767000042382, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0031480570003168395, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0022237099997255427, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0022237099997255427 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.049859716000128174, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005234030002156942, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004931600001327752, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004931600001327752 |
| }, |
| "communicator.exchange": { |
| "total": 0.04724041499980558, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04724041499980558 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016027379999741243, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00043804099959743326, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001164697000376691, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001164697000376691 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 521.3402854260212, |
| "count": 31601, |
| "is_parallel": true, |
| "self": 13.810498772056462, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 12.13946816904604, |
| "count": 31601, |
| "is_parallel": true, |
| "self": 12.13946816904604 |
| }, |
| "communicator.exchange": { |
| "total": 447.251706652964, |
| "count": 31601, |
| "is_parallel": true, |
| "self": 447.251706652964 |
| }, |
| "steps_from_proto": { |
| "total": 48.13861183195468, |
| "count": 31601, |
| "is_parallel": true, |
| "self": 11.131099037987951, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 37.007512793966725, |
| "count": 252808, |
| "is_parallel": true, |
| "self": 37.007512793966725 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 326.7334192610076, |
| "count": 31602, |
| "self": 0.9996612920335792, |
| "children": { |
| "process_trajectory": { |
| "total": 72.72581856197553, |
| "count": 31602, |
| "self": 72.62151894397562, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10429961799991361, |
| "count": 1, |
| "self": 0.10429961799991361 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 253.0079394069985, |
| "count": 214, |
| "self": 97.37822288999178, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 155.62971651700673, |
| "count": 11454, |
| "self": 155.62971651700673 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0670000847312622e-06, |
| "count": 1, |
| "self": 1.0670000847312622e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09280098299996098, |
| "count": 1, |
| "self": 0.0013448259996948764, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.0914561570002661, |
| "count": 1, |
| "self": 0.0914561570002661 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
