{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.11772998422384262, "min": 0.06954898685216904, "max": 1.324138879776001, "count": 7 }, "Pyramids.Policy.Entropy.sum": { "value": 3526.24853515625, "min": 2083.13134765625, "max": 40169.078125, "count": 7 }, "Pyramids.Step.mean": { "value": 209896.0, "min": 29952.0, "max": 209896.0, "count": 7 }, "Pyramids.Step.sum": { "value": 209896.0, "min": 29952.0, "max": 209896.0, "count": 7 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.10627956688404083, "min": -0.40380460023880005, "max": -0.10466883331537247, "count": 7 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -25.507095336914062, "min": -97.31690979003906, "max": -25.225189208984375, "count": 7 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.4675624370574951, "min": 1.4675624370574951, "max": 5.764090061187744, "count": 7 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 352.2149963378906, "min": 352.2149963378906, "max": 1389.145751953125, "count": 7 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.019694466279166885, "min": 0.015178072399942689, "max": 0.027342300717016713, "count": 7 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.2560280616291695, "min": 0.18213686879931226, "max": 0.2560280616291695, "count": 7 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.004094986796267649, "min": 0.004094986796267649, "max": 0.41671686099162175, "count": 7 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.05323482835147944, "min": 0.05323482835147944, "max": 2.9170180269413524, "count": 7 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002418489424606154, "min": 0.0002418489424606154, "max": 0.00029515063018788575, "count": 7 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.003144036251988, "min": 0.0020660544113152, "max": 0.0033771241742919997, "count": 7 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.18061630769230771, "min": 0.18061630769230771, "max": 0.19838354285714285, "count": 7 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.348012, "min": 1.3886848, "max": 2.425708, "count": 7 }, "Pyramids.Policy.Beta.mean": { "value": 0.008063569138461539, "min": 0.008063569138461539, "max": 0.00983851593142857, "count": 7 }, "Pyramids.Policy.Beta.sum": { "value": 0.10482639880000001, "min": 0.06886961152, "max": 0.11258822920000001, "count": 7 }, "Pyramids.Losses.RNDLoss.mean": { "value": 1.3876062631607056, "min": 1.3876062631607056, "max": 6.680552959442139, "count": 7 }, "Pyramids.Losses.RNDLoss.sum": { "value": 18.038881301879883, "min": 17.73118782043457, "max": 46.76387023925781, "count": 7 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 973.875, "max": 999.0, "count": 7 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30969.0, "min": 15984.0, "max": 32734.0, "count": 7 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9998968262826243, "min": -1.0000000521540642, "max": -0.7968188058584929, "count": 7 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -30.996801614761353, "min": -31.99640166759491, "max": -16.000000834465027, "count": 7 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9998968262826243, "min": -1.0000000521540642, "max": -0.7968188058584929, "count": 7 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -30.996801614761353, "min": -31.99640166759491, "max": -16.000000834465027, "count": 7 }, "Pyramids.Policy.RndReward.mean": { "value": 13.922048792723686, "min": 13.922048792723686, "max": 77.73568969242501, "count": 7 }, "Pyramids.Policy.RndReward.sum": { "value": 431.5835125744343, "min": 431.5835125744343, "max": 2565.277759850025, "count": 7 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701001801", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701002328" }, "total": 527.125634517, "count": 1, "self": 0.4865877850002107, "children": { "run_training.setup": { "total": 0.05713905999982671, "count": 1, "self": 0.05713905999982671 }, "TrainerController.start_learning": { "total": 526.5819076719999, "count": 1, "self": 0.46664083794030375, "children": { "TrainerController._reset_env": { "total": 4.376451669999824, "count": 1, "self": 4.376451669999824 }, "TrainerController.advance": { "total": 521.7375176260598, "count": 14321, "self": 0.48261267304269495, "children": { "env_step": { "total": 409.8400084350201, "count": 14321, "self": 365.1203195511034, "children": { "SubprocessEnvManager._take_step": { "total": 44.43252864797887, "count": 14321, "self": 1.4356362789935702, "children": { "TorchPolicy.evaluate": { "total": 42.9968923689853, "count": 14287, "self": 42.9968923689853 } } }, "workers": { "total": 0.2871602359377903, "count": 14320, "self": 0.0, "children": { "worker_root": { "total": 525.276098807984, "count": 14320, "is_parallel": true, "self": 196.39681395902744, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002671348999683687, "count": 1, "is_parallel": true, "self": 0.0007470840000678436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019242649996158434, "count": 8, "is_parallel": true, "self": 0.0019242649996158434 } } }, "UnityEnvironment.step": { "total": 0.12041197200005627, "count": 1, "is_parallel": true, "self": 0.0006894470006955089, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005085959996904421, "count": 1, "is_parallel": true, "self": 0.0005085959996904421 }, "communicator.exchange": { "total": 0.11724589100003868, "count": 1, "is_parallel": true, "self": 0.11724589100003868 }, "steps_from_proto": { "total": 0.0019680379996316333, "count": 1, "is_parallel": true, "self": 0.00043672499987224, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015313129997593933, "count": 8, "is_parallel": true, "self": 0.0015313129997593933 } } } } } } }, "UnityEnvironment.step": { "total": 328.87928484895656, "count": 14319, "is_parallel": true, "self": 9.117802288994426, "children": { "UnityEnvironment._generate_step_input": { "total": 6.496996475000742, "count": 14319, "is_parallel": true, "self": 6.496996475000742 }, "communicator.exchange": { "total": 285.87748170098484, "count": 14319, "is_parallel": true, "self": 285.87748170098484 }, "steps_from_proto": { "total": 27.387004383976546, "count": 14319, "is_parallel": true, "self": 5.848195669905181, "children": { "_process_rank_one_or_two_observation": { "total": 21.538808714071365, "count": 114552, "is_parallel": true, "self": 21.538808714071365 } } } } } } } } } } }, "trainer_advance": { "total": 111.41489651799702, "count": 14320, "self": 0.6273751060043651, "children": { "process_trajectory": { "total": 33.43045565899001, "count": 14320, "self": 33.43045565899001 }, "_update_policy": { "total": 77.35706575300264, "count": 86, "self": 60.008939288999954, "children": { "TorchPPOOptimizer.update": { "total": 17.34812646400269, "count": 621, "self": 17.34812646400269 } } } } } } }, "trainer_threads": { "total": 1.4990000636316836e-06, "count": 1, "self": 1.4990000636316836e-06 }, "TrainerController._save_models": { "total": 0.0012960389999534527, "count": 1, "self": 2.818100028889603e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0012678579996645567, "count": 1, "self": 0.0012678579996645567 } } } } } } }