{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2982460558414459, "min": 0.2788754403591156, "max": 0.39902108907699585, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 1479.3004150390625, "min": 1320.7540283203125, "max": 2101.974365234375, "count": 40 }, "Pyramids.Step.mean": { "value": 999897.0, "min": 804909.0, "max": 999897.0, "count": 40 }, "Pyramids.Step.sum": { "value": 999897.0, "min": 804909.0, "max": 999897.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3927173614501953, "min": 0.16222435235977173, "max": 0.6028797030448914, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 16.494129180908203, "min": 6.651198387145996, "max": 28.215749740600586, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010184453800320625, "min": -0.08904891461133957, "max": 0.010184453800320625, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.42774704098701477, "min": -3.918152093887329, "max": 0.42774704098701477, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 323.5, "min": 233.42857142857142, "max": 724.5, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 3235.0, "min": 1634.0, "max": 9158.0, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.476479971408844, "min": 0.5252249669283628, "max": 1.7665713897773199, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 14.76479971408844, "min": 4.201799735426903, "max": 26.457399681210518, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.476479971408844, "min": 0.5252249669283628, "max": 1.7665713897773199, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 14.76479971408844, "min": 4.201799735426903, "max": 26.457399681210518, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029189279896672814, "min": 0.02825928066990205, "max": 0.07618293218547478, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 0.29189279896672815, "min": 0.19781496468931437, "max": 0.9577268338762224, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06130017164590147, "min": 0.05845071774739255, "max": 0.07593325820441048, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.12260034329180294, "min": 0.11894674527381237, "max": 0.22379596517809353, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010486101050143287, "min": 0.0043403216695878655, "max": 0.018942632031717543, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.020972202100286573, "min": 0.008680643339175731, "max": 0.05682789609515263, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.000099750000001e-06, "min": 1.000099750000001e-06, "max": 7.873068031735001e-05, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.000199500000002e-06, "min": 2.000199500000002e-06, "max": 0.00022493464376640004, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10025, "min": 0.10025, "max": 0.11968265, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.2005, "min": 0.2005, "max": 0.35623360000000004, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 3.4975000000000023e-05, "min": 3.4975000000000023e-05, "max": 0.0019762967350000007, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 6.995000000000005e-05, "min": 6.995000000000005e-05, "max": 0.005647736640000001, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008905449882149696, "min": 0.008485357277095318, "max": 0.011165566742420197, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.017810899764299393, "min": 0.016970714554190636, "max": 0.03349670022726059, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690539927", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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 --resume", "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": "1690540447" }, "total": 519.894824899, "count": 1, "self": 0.9943624620009359, "children": { "run_training.setup": { "total": 0.03455513799963228, "count": 1, "self": 0.03455513799963228 }, "TrainerController.start_learning": { "total": 518.8659072989994, "count": 1, "self": 0.4367341879642481, "children": { "TrainerController._reset_env": { "total": 0.9879726039998786, "count": 1, "self": 0.9879726039998786 }, "TrainerController.advance": { "total": 517.3269477450358, "count": 12898, "self": 0.39302272900295065, "children": { "env_step": { "total": 343.16505507897364, "count": 12898, "self": 319.4674292979689, "children": { "SubprocessEnvManager._take_step": { "total": 23.42836658102169, "count": 12898, "self": 1.0010034780698334, "children": { "TorchPolicy.evaluate": { "total": 22.42736310295186, "count": 12556, "self": 22.42736310295186 } } }, "workers": { "total": 0.2692591999830256, "count": 12898, "self": 0.0, "children": { "worker_root": { "total": 517.6132438219938, "count": 12898, "is_parallel": true, "self": 225.79152497491395, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013732600000366801, "count": 1, "is_parallel": true, "self": 0.00038755100013077026, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009857089999059099, "count": 8, "is_parallel": true, "self": 0.0009857089999059099 } } }, "UnityEnvironment.step": { "total": 0.05134297599943238, "count": 1, "is_parallel": true, "self": 0.000539040000148816, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002860199992937851, "count": 1, "is_parallel": true, "self": 0.0002860199992937851 }, "communicator.exchange": { "total": 0.048784696999973676, "count": 1, "is_parallel": true, "self": 0.048784696999973676 }, "steps_from_proto": { "total": 0.0017332190000161063, "count": 1, "is_parallel": true, "self": 0.00035108899919578107, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013821300008203252, "count": 8, "is_parallel": true, "self": 0.0013821300008203252 } } } } } } }, "UnityEnvironment.step": { "total": 291.82171884707986, "count": 12897, "is_parallel": true, "self": 6.827149842975814, "children": { "UnityEnvironment._generate_step_input": { "total": 3.9066212840416483, "count": 12897, "is_parallel": true, "self": 3.9066212840416483 }, "communicator.exchange": { "total": 261.2293794990219, "count": 12897, "is_parallel": true, "self": 261.2293794990219 }, "steps_from_proto": { "total": 19.858568221040514, "count": 12897, "is_parallel": true, "self": 4.481742367082916, "children": { "_process_rank_one_or_two_observation": { "total": 15.376825853957598, "count": 103176, "is_parallel": true, "self": 15.376825853957598 } } } } } } } } } } }, "trainer_advance": { "total": 173.7688699370592, "count": 12898, "self": 0.9097520010345761, "children": { "process_trajectory": { "total": 24.18563149502552, "count": 12898, "self": 24.060020305026228, "children": { "RLTrainer._checkpoint": { "total": 0.12561118999929022, "count": 1, "self": 0.12561118999929022 } } }, "_update_policy": { "total": 148.6734864409991, "count": 94, "self": 61.99449725899649, "children": { "TorchPPOOptimizer.update": { "total": 86.67898918200262, "count": 4515, "self": 86.67898918200262 } } } } } } }, "trainer_threads": { "total": 1.2909995348309167e-06, "count": 1, "self": 1.2909995348309167e-06 }, "TrainerController._save_models": { "total": 0.11425147099998867, "count": 1, "self": 0.0019511899999997695, "children": { "RLTrainer._checkpoint": { "total": 0.1123002809999889, "count": 1, "self": 0.1123002809999889 } } } } } } }