| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.3987165689468384, |
| "min": 0.3861919343471527, |
| "max": 1.3533161878585815, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 11923.220703125, |
| "min": 11530.146484375, |
| "max": 41054.19921875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989988.0, |
| "min": 29952.0, |
| "max": 989988.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989988.0, |
| "min": 29952.0, |
| "max": 989988.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.41220057010650635, |
| "min": -0.09565431624650955, |
| "max": 0.4572250545024872, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 109.64535522460938, |
| "min": -23.052690505981445, |
| "max": 120.82069396972656, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.04009908810257912, |
| "min": -0.04009908810257912, |
| "max": 0.5330755710601807, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -10.666357040405273, |
| "min": -10.666357040405273, |
| "max": 126.33890533447266, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06777882515286494, |
| "min": 0.06493677061683098, |
| "max": 0.07318694618851143, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9489035521401092, |
| "min": 0.51230862331958, |
| "max": 1.0628151346269683, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015734387915429016, |
| "min": 0.0008547672344668508, |
| "max": 0.016256147493020186, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2202814308160062, |
| "min": 0.009402439579135358, |
| "max": 0.22758606490228261, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.307668992714284e-06, |
| "min": 7.307668992714284e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010230736589799998, |
| "min": 0.00010230736589799998, |
| "max": 0.0032549543150152994, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10243585714285715, |
| "min": 0.10243585714285715, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.434102, |
| "min": 1.3886848, |
| "max": 2.4435260000000003, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002533421285714285, |
| "min": 0.0002533421285714285, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003546789799999999, |
| "min": 0.003546789799999999, |
| "max": 0.10851997153000001, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.010972435586154461, |
| "min": 0.010972435586154461, |
| "max": 0.4800242781639099, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.1536141037940979, |
| "min": 0.1536141037940979, |
| "max": 3.3601698875427246, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 440.7647058823529, |
| "min": 407.42028985507244, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29972.0, |
| "min": 15984.0, |
| "max": 33045.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.4121470437111223, |
| "min": -1.0000000521540642, |
| "max": 1.5152221980194251, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 96.02599897235632, |
| "min": -29.998801574110985, |
| "max": 109.0959982573986, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.4121470437111223, |
| "min": -1.0000000521540642, |
| "max": 1.5152221980194251, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 96.02599897235632, |
| "min": -29.998801574110985, |
| "max": 109.0959982573986, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04895119851383189, |
| "min": 0.04867074583940532, |
| "max": 9.384271539747715, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.3286814989405684, |
| "min": 3.3286814989405684, |
| "max": 150.14834463596344, |
| "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": "1692516080", |
| "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=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": "1692518277" |
| }, |
| "total": 2196.401969502, |
| "count": 1, |
| "self": 0.43066244599958736, |
| "children": { |
| "run_training.setup": { |
| "total": 0.04695926900001268, |
| "count": 1, |
| "self": 0.04695926900001268 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2195.9243477870004, |
| "count": 1, |
| "self": 1.4222283420044732, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 5.070599105999918, |
| "count": 1, |
| "self": 5.070599105999918 |
| }, |
| "TrainerController.advance": { |
| "total": 2189.334574077996, |
| "count": 63625, |
| "self": 1.4117496020298859, |
| "children": { |
| "env_step": { |
| "total": 1536.9303757809505, |
| "count": 63625, |
| "self": 1426.4083871198518, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 109.67021155506427, |
| "count": 63625, |
| "self": 4.750360848044352, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 104.91985070701992, |
| "count": 62560, |
| "self": 104.91985070701992 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8517771060343193, |
| "count": 63625, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2191.0017423540503, |
| "count": 63625, |
| "is_parallel": true, |
| "self": 879.4796832140314, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0018444549999685478, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005373979997784772, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013070570001900705, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013070570001900705 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.0814473209999278, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005975269999680677, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00047899200001211284, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00047899200001211284 |
| }, |
| "communicator.exchange": { |
| "total": 0.07843964199992115, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.07843964199992115 |
| }, |
| "steps_from_proto": { |
| "total": 0.0019311600000264662, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003699930000493623, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015611669999771038, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015611669999771038 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1311.5220591400189, |
| "count": 63624, |
| "is_parallel": true, |
| "self": 33.91325898202581, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 22.924536279037852, |
| "count": 63624, |
| "is_parallel": true, |
| "self": 22.924536279037852 |
| }, |
| "communicator.exchange": { |
| "total": 1149.6489971579458, |
| "count": 63624, |
| "is_parallel": true, |
| "self": 1149.6489971579458 |
| }, |
| "steps_from_proto": { |
| "total": 105.0352667210093, |
| "count": 63624, |
| "is_parallel": true, |
| "self": 20.589172361947817, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 84.44609435906148, |
| "count": 508992, |
| "is_parallel": true, |
| "self": 84.44609435906148 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 650.9924486950158, |
| "count": 63625, |
| "self": 2.7003356991123155, |
| "children": { |
| "process_trajectory": { |
| "total": 109.49986051690928, |
| "count": 63625, |
| "self": 109.29078157690913, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.20907894000015403, |
| "count": 2, |
| "self": 0.20907894000015403 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 538.7922524789942, |
| "count": 445, |
| "self": 350.6468720720185, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 188.14538040697573, |
| "count": 22827, |
| "self": 188.14538040697573 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0000003385357559e-06, |
| "count": 1, |
| "self": 1.0000003385357559e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.0969452609997461, |
| "count": 1, |
| "self": 0.0014422259996536013, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.0955030350000925, |
| "count": 1, |
| "self": 0.0955030350000925 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
