{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45773938298225403, "min": 0.45773938298225403, "max": 1.3931586742401123, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13739.5048828125, "min": 13739.5048828125, "max": 42262.86328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989971.0, "min": 29960.0, "max": 989971.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989971.0, "min": 29960.0, "max": 989971.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.22304010391235352, "min": -0.11492698639631271, "max": 0.38267621397972107, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 57.0982666015625, "min": -27.582477569580078, "max": 101.02651977539062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004451883025467396, "min": -0.04713844135403633, "max": 0.3476746380329132, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.1396820545196533, "min": -12.491686820983887, "max": 82.74656677246094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07012159989556363, "min": 0.06579590197952041, "max": 0.07378204907944999, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9817023985378909, "min": 0.557657585452696, "max": 1.1067307361917498, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013110043325252176, "min": 0.0012155540885721808, "max": 0.024350446851654464, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18354060655353047, "min": 0.01701775724001053, "max": 0.3409062559231625, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.386418966464282e-06, "min": 7.386418966464282e-06, "max": 0.0002953059015647, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010340986553049995, "min": 0.00010340986553049995, "max": 0.0036310765896411996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246210714285713, "min": 0.10246210714285713, "max": 0.19843529999999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344694999999998, "min": 1.4344694999999998, "max": 2.6103587999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002559645035714285, "min": 0.0002559645035714285, "max": 0.00984368647, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003583503049999999, "min": 0.003583503049999999, "max": 0.12105484411999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011992411687970161, "min": 0.011462406255304813, "max": 0.4007926285266876, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16789376735687256, "min": 0.16047368943691254, "max": 3.206341028213501, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 559.1754385964912, "min": 464.6984126984127, "max": 997.7741935483871, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31873.0, "min": 16631.0, "max": 33546.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0840713899316532, "min": -0.9342129569380514, "max": 1.2812475957094678, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 60.70799783617258, "min": -28.960601665079594, "max": 80.71859852969646, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0840713899316532, "min": -0.9342129569380514, "max": 1.2812475957094678, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 60.70799783617258, "min": -28.960601665079594, "max": 80.71859852969646, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06890090299046799, "min": 0.057287835720671865, "max": 7.34049185759881, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.858450567466207, "min": 3.3836012388346717, "max": 124.78836157917976, "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": "1715092944", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715094983" }, "total": 2039.5154701539996, "count": 1, "self": 0.4873343350000141, "children": { "run_training.setup": { "total": 0.050293622999561194, "count": 1, "self": 0.050293622999561194 }, "TrainerController.start_learning": { "total": 2038.977842196, "count": 1, "self": 1.174734166897906, "children": { "TrainerController._reset_env": { "total": 2.178220691000206, "count": 1, "self": 2.178220691000206 }, "TrainerController.advance": { "total": 2035.5404128521013, "count": 63485, "self": 1.253859958119392, "children": { "env_step": { "total": 1420.5614851050323, "count": 63485, "self": 1298.9765406909955, "children": { "SubprocessEnvManager._take_step": { "total": 120.83334330204798, "count": 63485, "self": 4.446340922101626, "children": { "TorchPolicy.evaluate": { "total": 116.38700237994635, "count": 62573, "self": 116.38700237994635 } } }, "workers": { "total": 0.751601111988748, "count": 63485, "self": 0.0, "children": { "worker_root": { "total": 2034.2581471620433, "count": 63485, "is_parallel": true, "self": 848.2560148811026, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001984682000511384, "count": 1, "is_parallel": true, "self": 0.0006113299996286514, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013733520008827327, "count": 8, "is_parallel": true, "self": 0.0013733520008827327 } } }, "UnityEnvironment.step": { "total": 0.04858955999952741, "count": 1, "is_parallel": true, "self": 0.0006136749998404412, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004899869991277228, "count": 1, "is_parallel": true, "self": 0.0004899869991277228 }, "communicator.exchange": { "total": 0.04587207200074772, "count": 1, "is_parallel": true, "self": 0.04587207200074772 }, "steps_from_proto": { "total": 0.0016138259998115245, "count": 1, "is_parallel": true, "self": 0.0003284679987700656, "children": { "_process_rank_one_or_two_observation": { "total": 0.001285358001041459, "count": 8, "is_parallel": true, "self": 0.001285358001041459 } } } } } } }, "UnityEnvironment.step": { "total": 1186.0021322809407, "count": 63484, "is_parallel": true, "self": 33.4638846280468, "children": { "UnityEnvironment._generate_step_input": { "total": 22.79542943996603, "count": 63484, "is_parallel": true, "self": 22.79542943996603 }, "communicator.exchange": { "total": 1033.3370001790408, "count": 63484, "is_parallel": true, "self": 1033.3370001790408 }, "steps_from_proto": { "total": 96.40581803388704, "count": 63484, "is_parallel": true, "self": 18.92953789404055, "children": { "_process_rank_one_or_two_observation": { "total": 77.4762801398465, "count": 507872, "is_parallel": true, "self": 77.4762801398465 } } } } } } } } } } }, "trainer_advance": { "total": 613.7250677889497, "count": 63485, "self": 2.387112957055251, "children": { "process_trajectory": { "total": 123.9632755009061, "count": 63485, "self": 123.76481579090614, "children": { "RLTrainer._checkpoint": { "total": 0.19845970999995188, "count": 2, "self": 0.19845970999995188 } } }, "_update_policy": { "total": 487.37467933098833, "count": 456, "self": 286.87054537400127, "children": { "TorchPPOOptimizer.update": { "total": 200.50413395698706, "count": 22770, "self": 200.50413395698706 } } } } } } }, "trainer_threads": { "total": 8.030001481529325e-07, "count": 1, "self": 8.030001481529325e-07 }, "TrainerController._save_models": { "total": 0.0844736830003967, "count": 1, "self": 0.0015374290005638613, "children": { "RLTrainer._checkpoint": { "total": 0.08293625399983284, "count": 1, "self": 0.08293625399983284 } } } } } } }