{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6062504649162292, "min": 0.6062504649162292, "max": 1.5044150352478027, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18362.11328125, "min": 18362.11328125, "max": 45637.93359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989994.0, "min": 29952.0, "max": 989994.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989994.0, "min": 29952.0, "max": 989994.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3004736602306366, "min": -0.11869139224290848, "max": 0.403157502412796, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 78.12315368652344, "min": -28.723316192626953, "max": 107.23989868164062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.13697269558906555, "min": -0.13697269558906555, "max": 0.29885903000831604, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -35.61289978027344, "min": -35.61289978027344, "max": 70.82958984375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06720543275548128, "min": 0.06414307272863896, "max": 0.07372505681373046, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9408760585767381, "min": 0.4934527312191979, "max": 1.0769256985901545, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014498068344913748, "min": 0.0005441277505770165, "max": 0.014498068344913748, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20297295682879246, "min": 0.004353022004616132, "max": 0.20297295682879246, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.564490335678568e-06, "min": 7.564490335678568e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010590286469949995, "min": 0.00010590286469949995, "max": 0.0032236816254395, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252146428571429, "min": 0.10252146428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353005, "min": 1.3691136000000002, "max": 2.3592725999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000261894282142857, "min": 0.000261894282142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036665199499999984, "min": 0.0036665199499999984, "max": 0.10746859394999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007226922549307346, "min": 0.007226922549307346, "max": 0.3170693516731262, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.101176917552948, "min": 0.101176917552948, "max": 2.2194855213165283, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 539.6315789473684, "min": 470.3492063492063, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30759.0, "min": 15984.0, "max": 32695.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1795718941772193, "min": -1.0000000521540642, "max": 1.3708761711678807, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 67.2355979681015, "min": -32.000001668930054, "max": 86.36519878357649, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1795718941772193, "min": -1.0000000521540642, "max": 1.3708761711678807, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 67.2355979681015, "min": -32.000001668930054, "max": 86.36519878357649, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04060403006906997, "min": 0.038298672050344366, "max": 6.31628477666527, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3144297139369883, "min": 2.297920323020662, "max": 101.06055642664433, "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": "1679910598", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1679912638" }, "total": 2039.381435795, "count": 1, "self": 0.8492705809999279, "children": { "run_training.setup": { "total": 0.1288634849997834, "count": 1, "self": 0.1288634849997834 }, "TrainerController.start_learning": { "total": 2038.4033017290003, "count": 1, "self": 1.2718725699678544, "children": { "TrainerController._reset_env": { "total": 7.329010131000359, "count": 1, "self": 7.329010131000359 }, "TrainerController.advance": { "total": 2029.6636828010323, "count": 63448, "self": 1.369906917017488, "children": { "env_step": { "total": 1404.6409445250247, "count": 63448, "self": 1300.4712432920323, "children": { "SubprocessEnvManager._take_step": { "total": 103.3917156010234, "count": 63448, "self": 4.487019692956437, "children": { "TorchPolicy.evaluate": { "total": 98.90469590806697, "count": 62576, "self": 98.90469590806697 } } }, "workers": { "total": 0.7779856319689316, "count": 63448, "self": 0.0, "children": { "worker_root": { "total": 2034.2874729140103, "count": 63448, "is_parallel": true, "self": 844.0437514310161, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025731410000844335, "count": 1, "is_parallel": true, "self": 0.0007599059995300195, "children": { "_process_rank_one_or_two_observation": { "total": 0.001813235000554414, "count": 8, "is_parallel": true, "self": 0.001813235000554414 } } }, "UnityEnvironment.step": { "total": 0.046577025999795296, "count": 1, "is_parallel": true, "self": 0.0004970700001649675, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004483230000005278, "count": 1, "is_parallel": true, "self": 0.0004483230000005278 }, "communicator.exchange": { "total": 0.04408319799995297, "count": 1, "is_parallel": true, "self": 0.04408319799995297 }, "steps_from_proto": { "total": 0.0015484349996768287, "count": 1, "is_parallel": true, "self": 0.00035262599976704223, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011958089999097865, "count": 8, "is_parallel": true, "self": 0.0011958089999097865 } } } } } } }, "UnityEnvironment.step": { "total": 1190.2437214829943, "count": 63447, "is_parallel": true, "self": 30.59192993200486, "children": { "UnityEnvironment._generate_step_input": { "total": 22.688013416060585, "count": 63447, "is_parallel": true, "self": 22.688013416060585 }, "communicator.exchange": { "total": 1047.8604596649166, "count": 63447, "is_parallel": true, "self": 1047.8604596649166 }, "steps_from_proto": { "total": 89.10331847001225, "count": 63447, "is_parallel": true, "self": 18.68505618512654, "children": { "_process_rank_one_or_two_observation": { "total": 70.41826228488571, "count": 507576, "is_parallel": true, "self": 70.41826228488571 } } } } } } } } } } }, "trainer_advance": { "total": 623.6528313589902, "count": 63448, "self": 2.3618430740048098, "children": { "process_trajectory": { "total": 114.39431535998165, "count": 63448, "self": 114.1500248399816, "children": { "RLTrainer._checkpoint": { "total": 0.24429052000004958, "count": 2, "self": 0.24429052000004958 } } }, "_update_policy": { "total": 506.8966729250037, "count": 439, "self": 323.0693864280106, "children": { "TorchPPOOptimizer.update": { "total": 183.8272864969931, "count": 22866, "self": 183.8272864969931 } } } } } } }, "trainer_threads": { "total": 1.0750000001280569e-06, "count": 1, "self": 1.0750000001280569e-06 }, "TrainerController._save_models": { "total": 0.13873515199975373, "count": 1, "self": 0.0018474649996278458, "children": { "RLTrainer._checkpoint": { "total": 0.13688768700012588, "count": 1, "self": 0.13688768700012588 } } } } } } }