{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.20806019008159637, "min": 0.20498721301555634, "max": 1.4087297916412354, "count": 68 }, "Pyramids.Policy.Entropy.sum": { "value": 6258.45068359375, "min": 6162.7353515625, "max": 42735.2265625, "count": 68 }, "Pyramids.Step.mean": { "value": 2039974.0, "min": 29952.0, "max": 2039974.0, "count": 68 }, "Pyramids.Step.sum": { "value": 2039974.0, "min": 29952.0, "max": 2039974.0, "count": 68 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7180836796760559, "min": -0.202459454536438, "max": 0.8391205668449402, "count": 68 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 206.0900115966797, "min": -47.98289108276367, "max": 253.41441345214844, "count": 68 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01974889449775219, "min": -0.020745186135172844, "max": 0.3012049198150635, "count": 68 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.667932987213135, "min": -5.642690658569336, "max": 72.59038543701172, "count": 68 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06994604640598469, "min": 0.06437926069927578, "max": 0.07542860652805558, "count": 68 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0491906960897703, "min": 0.4997173156605996, "max": 1.1203702781543445, "count": 68 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012934513574559698, "min": 0.00020215898771885126, "max": 0.01674720939523208, "count": 68 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1940177036183955, "min": 0.002425907852626215, "max": 0.24775536607679288, "count": 68 }, "Pyramids.Policy.LearningRate.mean": { "value": 9.751318749562666e-05, "min": 9.751318749562666e-05, "max": 0.00029838354339596195, "count": 68 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0014626978124344, "min": 0.0014082724305761664, "max": 0.003884402105199333, "count": 68 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.13250437333333334, "min": 0.13250437333333334, "max": 0.19946118095238097, "count": 68 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.9875656000000002, "min": 1.3962282666666668, "max": 2.7375138333333333, "count": 68 }, "Pyramids.Policy.Beta.mean": { "value": 0.0032571868960000003, "min": 0.0032571868960000003, "max": 0.009946171977142856, "count": 68 }, "Pyramids.Policy.Beta.sum": { "value": 0.04885780344000001, "min": 0.04703544095000001, "max": 0.1294905866, "count": 68 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006178003270179033, "min": 0.006178003270179033, "max": 0.3926575779914856, "count": 68 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09267004579305649, "min": 0.08850584924221039, "max": 2.748603105545044, "count": 68 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 282.5, "min": 230.015503875969, "max": 999.0, "count": 68 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31075.0, "min": 15984.0, "max": 33139.0, "count": 68 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6447508950802412, "min": -1.0000000521540642, "max": 1.771099990606308, "count": 68 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 180.92259845882654, "min": -31.996801674365997, "max": 230.24299877882004, "count": 68 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6447508950802412, "min": -1.0000000521540642, "max": 1.771099990606308, "count": 68 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 180.92259845882654, "min": -31.996801674365997, "max": 230.24299877882004, "count": 68 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018122928221551277, "min": 0.01627527468313369, "max": 7.2424637991935015, "count": 68 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9935221043706406, "min": 1.8976759276065422, "max": 115.87942078709602, "count": 68 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 68 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 68 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682075130", "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": "1682082854" }, "total": 7724.067445713, "count": 1, "self": 1.8023621080001249, "children": { "run_training.setup": { "total": 0.1436704740000323, "count": 1, "self": 0.1436704740000323 }, "TrainerController.start_learning": { "total": 7722.121413131, "count": 1, "self": 5.208369556036814, "children": { "TrainerController._reset_env": { "total": 1.14567587800002, "count": 1, "self": 1.14567587800002 }, "TrainerController.advance": { "total": 7715.762792701962, "count": 132365, "self": 5.294990161900387, "children": { "env_step": { "total": 5294.4955240709605, "count": 132365, "self": 4998.463637665089, "children": { "SubprocessEnvManager._take_step": { "total": 292.93874536886113, "count": 132365, "self": 15.41742255680498, "children": { "TorchPolicy.evaluate": { "total": 277.52132281205616, "count": 128224, "self": 277.52132281205616 } } }, "workers": { "total": 3.093141037010696, "count": 132364, "self": 0.0, "children": { "worker_root": { "total": 7705.245057048907, "count": 132364, "is_parallel": true, "self": 3081.743578485707, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005620684000007259, "count": 1, "is_parallel": true, "self": 0.004074306000063643, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015463779999436156, "count": 8, "is_parallel": true, "self": 0.0015463779999436156 } } }, "UnityEnvironment.step": { "total": 0.06448598100001846, "count": 1, "is_parallel": true, "self": 0.000694903000010072, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005833970000139743, "count": 1, "is_parallel": true, "self": 0.0005833970000139743 }, "communicator.exchange": { "total": 0.06092713800001093, "count": 1, "is_parallel": true, "self": 0.06092713800001093 }, "steps_from_proto": { "total": 0.0022805429999834814, "count": 1, "is_parallel": true, "self": 0.0005486009998776353, "children": { "_process_rank_one_or_two_observation": { "total": 0.001731942000105846, "count": 8, "is_parallel": true, "self": 0.001731942000105846 } } } } } } }, "UnityEnvironment.step": { "total": 4623.5014785632, "count": 132363, "is_parallel": true, "self": 99.95069833044181, "children": { "UnityEnvironment._generate_step_input": { "total": 57.772741602772385, "count": 132363, "is_parallel": true, "self": 57.772741602772385 }, "communicator.exchange": { "total": 4180.635670287057, "count": 132363, "is_parallel": true, "self": 4180.635670287057 }, "steps_from_proto": { "total": 285.14236834292876, "count": 132363, "is_parallel": true, "self": 65.43341531317373, "children": { "_process_rank_one_or_two_observation": { "total": 219.70895302975504, "count": 1058904, "is_parallel": true, "self": 219.70895302975504 } } } } } } } } } } }, "trainer_advance": { "total": 2415.972278469101, "count": 132364, "self": 9.911259326296658, "children": { "process_trajectory": { "total": 315.03257293481346, "count": 132364, "self": 314.33420021681417, "children": { "RLTrainer._checkpoint": { "total": 0.6983727179992911, "count": 4, "self": 0.6983727179992911 } } }, "_update_policy": { "total": 2091.0284462079912, "count": 945, "self": 833.4558960000006, "children": { "TorchPPOOptimizer.update": { "total": 1257.5725502079906, "count": 46722, "self": 1257.5725502079906 } } } } } } }, "trainer_threads": { "total": 1.9799999790848233e-06, "count": 1, "self": 1.9799999790848233e-06 }, "TrainerController._save_models": { "total": 0.0045730150004601455, "count": 1, "self": 4.118800006835954e-05, "children": { "RLTrainer._checkpoint": { "total": 0.004531827000391786, "count": 1, "self": 0.004531827000391786 } } } } } } }