{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39078158140182495, "min": 0.39078158140182495, "max": 0.959633469581604, "count": 26 }, "Pyramids.Policy.Entropy.sum": { "value": 11767.21484375, "min": 1467.0263671875, "max": 28742.94140625, "count": 26 }, "Pyramids.Step.mean": { "value": 989894.0, "min": 239955.0, "max": 989894.0, "count": 26 }, "Pyramids.Step.sum": { "value": 989894.0, "min": 239955.0, "max": 989894.0, "count": 26 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.42578125, "min": -0.11405441910028458, "max": 0.48761728405952454, "count": 26 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 111.12890625, "min": -22.48892593383789, "max": 133.49281311035156, "count": 26 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015334302559494972, "min": -0.0005214456468820572, "max": 0.06604637205600739, "count": 26 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.00225305557251, "min": -0.1439189910888672, "max": 12.465400695800781, "count": 26 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 26 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 26 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06877448264007582, "min": 0.06547761583860835, "max": 0.07437893156935199, "count": 25 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9628427569610615, "min": 0.7144435800909108, "max": 1.0666395878846135, "count": 25 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014782466559844673, "min": 0.0006058385635895857, "max": 0.01599865179984287, "count": 25 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20695453183782542, "min": 0.007270062763075029, "max": 0.23746241712069607, "count": 25 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.2895189987642845e-06, "min": 7.2895189987642845e-06, "max": 0.00022304366565211998, "count": 25 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010205326598269998, "min": 0.00010205326598269998, "max": 0.0025510507496499003, "count": 25 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242980714285717, "min": 0.10242980714285717, "max": 0.17434787999999998, "count": 25 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340173000000003, "min": 1.4340173000000003, "max": 2.190688, "count": 25 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025273773357142854, "min": 0.00025273773357142854, "max": 0.007437353212, "count": 25 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035383282699999997, "min": 0.0035383282699999997, "max": 0.08507997499, "count": 25 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011967487633228302, "min": 0.011967487633228302, "max": 0.04896247014403343, "count": 25 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16754482686519623, "min": 0.16754482686519623, "max": 0.4896247088909149, "count": 25 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 409.95588235294116, "min": 367.0, "max": 994.4117647058823, "count": 25 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27877.0, "min": 16905.0, "max": 32634.0, "count": 25 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3546793781878317, "min": -0.9292000523119262, "max": 1.5588987494508426, "count": 25 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 92.11819771677256, "min": -30.663601726293564, "max": 126.27079870551825, "count": 25 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3546793781878317, "min": -0.9292000523119262, "max": 1.5588987494508426, "count": 25 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 92.11819771677256, "min": -30.663601726293564, "max": 126.27079870551825, "count": 25 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05098443436851513, "min": 0.05098443436851513, "max": 0.5046917924746162, "count": 25 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4669415370590286, "min": 3.4669415370590286, "max": 13.512158337049186, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1673437582", "python_version": "3.8.9 (default, Jan 11 2023, 11:43:45) \n[GCC 8.5.0 20210514 (Red Hat 8.5.0-10)]", "command_line_arguments": "/home/marco/.virtualenvs/ml38/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics --resume", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.2+cu111", "numpy_version": "1.23.5", "end_time_seconds": "1673438813" }, "total": 1230.21500122, "count": 1, "self": 0.5250316530000418, "children": { "run_training.setup": { "total": 0.04993825498968363, "count": 1, "self": 0.04993825498968363 }, "TrainerController.start_learning": { "total": 1229.6400313120103, "count": 1, "self": 0.873780082212761, "children": { "TrainerController._reset_env": { "total": 16.60682203900069, "count": 1, "self": 16.60682203900069 }, "TrainerController.advance": { "total": 1211.900818651804, "count": 48449, "self": 0.8250228467804845, "children": { "env_step": { "total": 724.8020726982213, "count": 48449, "self": 653.9688999232894, "children": { "SubprocessEnvManager._take_step": { "total": 70.30755756580038, "count": 48449, "self": 2.880844031518791, "children": { "TorchPolicy.evaluate": { "total": 67.42671353428159, "count": 47609, "self": 21.31115324224811, "children": { "TorchPolicy.sample_actions": { "total": 46.11556029203348, "count": 47609, "self": 46.11556029203348 } } } } }, "workers": { "total": 0.5256152091315016, "count": 48449, "self": 0.0, "children": { "worker_root": { "total": 1227.7564379225078, "count": 48449, "is_parallel": true, "self": 641.0297609794361, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017990200140047818, "count": 1, "is_parallel": true, "self": 0.0006898560677655041, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011091639462392777, "count": 8, "is_parallel": true, "self": 0.0011091639462392777 } } }, "UnityEnvironment.step": { "total": 0.03202838698052801, "count": 1, "is_parallel": true, "self": 0.0003686369745992124, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003417220141272992, "count": 1, "is_parallel": true, "self": 0.0003417220141272992 }, "communicator.exchange": { "total": 0.030225806985981762, "count": 1, "is_parallel": true, "self": 0.030225806985981762 }, "steps_from_proto": { "total": 0.001092221005819738, "count": 1, "is_parallel": true, "self": 0.00031756097450852394, "children": { "_process_rank_one_or_two_observation": { "total": 0.000774660031311214, "count": 8, "is_parallel": true, "self": 0.000774660031311214 } } } } } } }, "UnityEnvironment.step": { "total": 586.7266769430717, "count": 48448, "is_parallel": true, "self": 14.195466856646817, "children": { "UnityEnvironment._generate_step_input": { "total": 10.359452535078162, "count": 48448, "is_parallel": true, "self": 10.359452535078162 }, "communicator.exchange": { "total": 519.3050258742296, "count": 48448, "is_parallel": true, "self": 519.3050258742296 }, "steps_from_proto": { "total": 42.86673167711706, "count": 48448, "is_parallel": true, "self": 10.673247159080347, "children": { "_process_rank_one_or_two_observation": { "total": 32.19348451803671, "count": 387584, "is_parallel": true, "self": 32.19348451803671 } } } } } } } } } } }, "trainer_advance": { "total": 486.2737231068022, "count": 48449, "self": 1.542325942980824, "children": { "process_trajectory": { "total": 103.32331446980243, "count": 48449, "self": 102.71449498078437, "children": { "RLTrainer._checkpoint": { "total": 0.6088194890180603, "count": 2, "self": 0.6088194890180603 } } }, "_update_policy": { "total": 381.40808269401896, "count": 344, "self": 134.51145814190386, "children": { "TorchPPOOptimizer.update": { "total": 246.8966245521151, "count": 17316, "self": 246.8966245521151 } } } } } } }, "trainer_threads": { "total": 9.709910955280066e-07, "count": 1, "self": 9.709910955280066e-07 }, "TrainerController._save_models": { "total": 0.25860956800170243, "count": 1, "self": 0.014524578000418842, "children": { "RLTrainer._checkpoint": { "total": 0.24408499000128359, "count": 1, "self": 0.24408499000128359 } } } } } } }