| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.1988169550895691, |
| "min": 0.19206389784812927, |
| "max": 1.434348702430725, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 5932.69775390625, |
| "min": 5734.259765625, |
| "max": 43512.40234375, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999944.0, |
| "min": 29952.0, |
| "max": 2999944.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999944.0, |
| "min": 29952.0, |
| "max": 2999944.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.8122171759605408, |
| "min": -0.09197285771369934, |
| "max": 0.8575071692466736, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 244.4773712158203, |
| "min": -22.16545867919922, |
| "max": 262.78973388671875, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.00868191383779049, |
| "min": -0.00887167640030384, |
| "max": 0.2770327925682068, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 2.6132559776306152, |
| "min": -2.528427839279175, |
| "max": 66.76490020751953, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07044893840161713, |
| "min": 0.06454850049340168, |
| "max": 0.07387519714432887, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9862851376226399, |
| "min": 0.5136050894523932, |
| "max": 1.0757815294103543, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015438501793016937, |
| "min": 0.0012278925777686634, |
| "max": 0.016215821330072634, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21613902510223712, |
| "min": 0.017190496088761286, |
| "max": 0.23983306943167307, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.4271209528976184e-06, |
| "min": 1.4271209528976184e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 1.9979693340566658e-05, |
| "min": 1.9979693340566658e-05, |
| "max": 0.0040108212630596, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10047567380952381, |
| "min": 0.10047567380952381, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4066594333333333, |
| "min": 1.3962282666666668, |
| "max": 2.7975181333333334, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.751981357142856e-05, |
| "min": 5.751981357142856e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008052773899999998, |
| "min": 0.0008052773899999998, |
| "max": 0.13370034596000002, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.006686483044177294, |
| "min": 0.006640144158154726, |
| "max": 0.46720370650291443, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.09361076354980469, |
| "min": 0.09361076354980469, |
| "max": 3.270426034927368, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 212.95714285714286, |
| "min": 210.27205882352942, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29814.0, |
| "min": 15984.0, |
| "max": 32832.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.758461415448359, |
| "min": -1.0000000521540642, |
| "max": 1.7888880961841636, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 246.18459816277027, |
| "min": -28.386001624166965, |
| "max": 260.2317970842123, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.758461415448359, |
| "min": -1.0000000521540642, |
| "max": 1.7888880961841636, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 246.18459816277027, |
| "min": -28.386001624166965, |
| "max": 260.2317970842123, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.014785116313890154, |
| "min": 0.014785116313890154, |
| "max": 8.86121528595686, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.0699162839446217, |
| "min": 2.0002739055489656, |
| "max": 141.77944457530975, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1684477697", |
| "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1684484802" |
| }, |
| "total": 7104.767843387999, |
| "count": 1, |
| "self": 0.492580159998397, |
| "children": { |
| "run_training.setup": { |
| "total": 0.03943746899994949, |
| "count": 1, |
| "self": 0.03943746899994949 |
| }, |
| "TrainerController.start_learning": { |
| "total": 7104.235825759, |
| "count": 1, |
| "self": 3.955343240102593, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 4.219599223999921, |
| "count": 1, |
| "self": 4.219599223999921 |
| }, |
| "TrainerController.advance": { |
| "total": 7095.969203339899, |
| "count": 195233, |
| "self": 4.038991887908196, |
| "children": { |
| "env_step": { |
| "total": 5238.759162955104, |
| "count": 195233, |
| "self": 4921.734101820209, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 314.65616385813905, |
| "count": 195233, |
| "self": 13.709423154227125, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 300.9467407039119, |
| "count": 187548, |
| "self": 300.9467407039119 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.3688972767567975, |
| "count": 195233, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 7089.621153355885, |
| "count": 195233, |
| "is_parallel": true, |
| "self": 2499.8738603888896, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0050962069999513915, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0037752559999262303, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013209510000251612, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013209510000251612 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.08074061899992557, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005537010001717135, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004516199999216042, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004516199999216042 |
| }, |
| "communicator.exchange": { |
| "total": 0.07788626999990811, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.07788626999990811 |
| }, |
| "steps_from_proto": { |
| "total": 0.0018490279999241466, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003722559995367192, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014767720003874274, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014767720003874274 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 4589.747292966996, |
| "count": 195232, |
| "is_parallel": true, |
| "self": 93.91463720320917, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 68.4400304708106, |
| "count": 195232, |
| "is_parallel": true, |
| "self": 68.4400304708106 |
| }, |
| "communicator.exchange": { |
| "total": 4132.943185663907, |
| "count": 195232, |
| "is_parallel": true, |
| "self": 4132.943185663907 |
| }, |
| "steps_from_proto": { |
| "total": 294.44943962906905, |
| "count": 195232, |
| "is_parallel": true, |
| "self": 59.74682044704036, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 234.70261918202868, |
| "count": 1561856, |
| "is_parallel": true, |
| "self": 234.70261918202868 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1853.1710484968864, |
| "count": 195233, |
| "self": 8.148577013893373, |
| "children": { |
| "process_trajectory": { |
| "total": 327.0531461749947, |
| "count": 195233, |
| "self": 326.37077931499425, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.6823668600004567, |
| "count": 6, |
| "self": 0.6823668600004567 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1517.9693253079984, |
| "count": 1402, |
| "self": 967.9629435879424, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 550.006381720056, |
| "count": 68424, |
| "self": 550.006381720056 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.02400008472614e-06, |
| "count": 1, |
| "self": 1.02400008472614e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09167893099947833, |
| "count": 1, |
| "self": 0.0014176540007611038, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09026127699871722, |
| "count": 1, |
| "self": 0.09026127699871722 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
