| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.6780926585197449, |
| "min": 0.6780926585197449, |
| "max": 1.4966082572937012, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 20386.177734375, |
| "min": 20386.177734375, |
| "max": 45401.109375, |
| "count": 16 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 479994.0, |
| "min": 29952.0, |
| "max": 479994.0, |
| "count": 16 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 479994.0, |
| "min": 29952.0, |
| "max": 479994.0, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.1414555460214615, |
| "min": -0.23639164865016937, |
| "max": 0.14906920492649078, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 35.929710388183594, |
| "min": -56.02482223510742, |
| "max": 38.01264572143555, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.018116425722837448, |
| "min": 0.018116425722837448, |
| "max": 0.5567641258239746, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 4.601572036743164, |
| "min": 4.601572036743164, |
| "max": 131.95309448242188, |
| "count": 16 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06645105248939145, |
| "min": 0.06645105248939145, |
| "max": 0.07467537732261417, |
| "count": 16 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9303147348514804, |
| "min": 0.4955608299940064, |
| "max": 1.0468565652776947, |
| "count": 16 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.010426111478478226, |
| "min": 0.001092508444267564, |
| "max": 0.010426111478478226, |
| "count": 16 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.14596556069869515, |
| "min": 0.014202609775478332, |
| "max": 0.14596556069869515, |
| "count": 16 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 2.0531364584814284e-05, |
| "min": 2.0531364584814284e-05, |
| "max": 0.00029030126037577137, |
| "count": 16 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0002874391041874, |
| "min": 0.0002874391041874, |
| "max": 0.0030851468716178, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10684375714285717, |
| "min": 0.10684375714285717, |
| "max": 0.19676708571428575, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4958126000000003, |
| "min": 1.3773696000000002, |
| "max": 2.4223424000000002, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0006936913385714286, |
| "min": 0.0006936913385714286, |
| "max": 0.00967703186285714, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00971167874, |
| "min": 0.00971167874, |
| "max": 0.10286538178000001, |
| "count": 16 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.024218371137976646, |
| "min": 0.024218371137976646, |
| "max": 0.4899718761444092, |
| "count": 16 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.33905720710754395, |
| "min": 0.33905720710754395, |
| "max": 3.4298031330108643, |
| "count": 16 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 666.3333333333334, |
| "min": 656.1041666666666, |
| "max": 999.0, |
| "count": 16 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29985.0, |
| "min": 15984.0, |
| "max": 33294.0, |
| "count": 16 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 0.7112221856911977, |
| "min": -1.0000000521540642, |
| "max": 0.7112221856911977, |
| "count": 16 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 32.0049983561039, |
| "min": -28.351401582360268, |
| "max": 32.0049983561039, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 0.7112221856911977, |
| "min": -1.0000000521540642, |
| "max": 0.7112221856911977, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 32.0049983561039, |
| "min": -28.351401582360268, |
| "max": 32.0049983561039, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.16815830469907572, |
| "min": 0.16815830469907572, |
| "max": 9.896126369014382, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 7.567123711458407, |
| "min": 7.567123711458407, |
| "max": 158.33802190423012, |
| "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": "1665470593", |
| "python_version": "3.7.14 (default, Sep 8 2022, 00:06:44) \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 Training1 --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": "1665471614" |
| }, |
| "total": 1021.506240728, |
| "count": 1, |
| "self": 0.4404604270000618, |
| "children": { |
| "run_training.setup": { |
| "total": 0.04403185699993628, |
| "count": 1, |
| "self": 0.04403185699993628 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1021.021748444, |
| "count": 1, |
| "self": 0.703151976004392, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 7.764869113999907, |
| "count": 1, |
| "self": 7.764869113999907 |
| }, |
| "TrainerController.advance": { |
| "total": 1012.4568733779957, |
| "count": 31679, |
| "self": 0.7520124779896378, |
| "children": { |
| "env_step": { |
| "total": 658.317399679996, |
| "count": 31679, |
| "self": 604.5322586079994, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 53.409566274000895, |
| "count": 31679, |
| "self": 2.3027494919753053, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 51.10681678202559, |
| "count": 31325, |
| "self": 17.500401420018193, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 33.6064153620074, |
| "count": 31325, |
| "self": 33.6064153620074 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.3755747979956823, |
| "count": 31679, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1018.6875208179723, |
| "count": 31679, |
| "is_parallel": true, |
| "self": 465.00155359596056, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.004951518000098076, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.003698659000065163, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012528590000329132, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012528590000329132 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04412596800000301, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00048330499987514486, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00042965900001945556, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00042965900001945556 |
| }, |
| "communicator.exchange": { |
| "total": 0.041634889000079056, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.041634889000079056 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015781150000293565, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00042431500003203837, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001153799999997318, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001153799999997318 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 553.6859672220118, |
| "count": 31678, |
| "is_parallel": true, |
| "self": 14.306175649968509, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 11.72681195101029, |
| "count": 31678, |
| "is_parallel": true, |
| "self": 11.72681195101029 |
| }, |
| "communicator.exchange": { |
| "total": 480.9040272120109, |
| "count": 31678, |
| "is_parallel": true, |
| "self": 480.9040272120109 |
| }, |
| "steps_from_proto": { |
| "total": 46.74895240902208, |
| "count": 31678, |
| "is_parallel": true, |
| "self": 11.697514713026862, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 35.05143769599522, |
| "count": 253424, |
| "is_parallel": true, |
| "self": 35.05143769599522 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 353.3874612200101, |
| "count": 31679, |
| "self": 1.2335903209998378, |
| "children": { |
| "process_trajectory": { |
| "total": 79.01677286501103, |
| "count": 31679, |
| "self": 78.91217545701102, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10459740800001782, |
| "count": 1, |
| "self": 0.10459740800001782 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 273.1370980339992, |
| "count": 220, |
| "self": 108.45097066998869, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 164.68612736401053, |
| "count": 11376, |
| "self": 164.68612736401053 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.339998996438226e-07, |
| "count": 1, |
| "self": 9.339998996438226e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09685304200002065, |
| "count": 1, |
| "self": 0.0016681140000400774, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09518492799998057, |
| "count": 1, |
| "self": 0.09518492799998057 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
