{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.12670837342739105, "min": 0.11482398957014084, "max": 1.432744026184082, "count": 133 }, "Pyramids.Policy.Entropy.sum": { "value": 3803.278564453125, "min": 3494.0546875, "max": 43463.72265625, "count": 133 }, "Pyramids.Step.mean": { "value": 3989975.0, "min": 29971.0, "max": 3989975.0, "count": 133 }, "Pyramids.Step.sum": { "value": 3989975.0, "min": 29971.0, "max": 3989975.0, "count": 133 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7838701009750366, "min": -0.09785117208957672, "max": 0.8745713829994202, "count": 133 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 234.37716674804688, "min": -23.386430740356445, "max": 268.493408203125, "count": 133 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023109685629606247, "min": -0.034248895943164825, "max": 0.28882038593292236, "count": 133 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.909795761108398, "min": -10.000677108764648, "max": 69.89453125, "count": 133 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06718324957958734, "min": 0.06507172040486088, "max": 0.07457860413290163, "count": 133 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.00774874369381, "min": 0.48327235322533946, "max": 1.0781306636927184, "count": 133 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015728502631989414, "min": 0.0002528220798020153, "max": 0.01734278085530691, "count": 133 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2359275394798412, "min": 0.0027810428778221683, "max": 0.2572132958642518, "count": 133 }, "Pyramids.Policy.LearningRate.mean": { "value": 6.260660407000012e-07, "min": 6.260660407000012e-07, "max": 9.960313253972498e-05, "count": 133 }, "Pyramids.Policy.LearningRate.sum": { "value": 9.390990610500018e-06, "min": 9.390990610500018e-06, "max": 0.001348149676850475, "count": 133 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10062596666666669, "min": 0.10062596666666669, "max": 0.19960313214285713, "count": 133 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5093895000000004, "min": 1.397221925, "max": 2.848149525, "count": 133 }, "Pyramids.Policy.Beta.mean": { "value": 7.253407000000012e-05, "min": 7.253407000000012e-05, "max": 0.009960352901071428, "count": 133 }, "Pyramids.Policy.Beta.sum": { "value": 0.0010880110500000018, "min": 0.0010880110500000018, "max": 0.1348301375475, "count": 133 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00683261314406991, "min": 0.0066736722365021706, "max": 0.47220566868782043, "count": 133 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10248919576406479, "min": 0.09343141317367554, "max": 3.3054397106170654, "count": 133 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 218.42857142857142, "min": 203.95862068965516, "max": 999.0, "count": 133 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30580.0, "min": 16642.0, "max": 33971.0, "count": 133 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7668043058767593, "min": -0.9999226322097163, "max": 1.7962916558608413, "count": 133 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 245.58579851686954, "min": -30.997601598501205, "max": 258.66599844396114, "count": 133 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7668043058767593, "min": -0.9999226322097163, "max": 1.7962916558608413, "count": 133 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 245.58579851686954, "min": -30.997601598501205, "max": 258.66599844396114, "count": 133 }, "Pyramids.Policy.RndReward.mean": { "value": 0.015469531422312808, "min": 0.015313875367616851, "max": 8.606373690287857, "count": 133 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1502648677014804, "min": 2.037322950680391, "max": 146.30835273489356, "count": 133 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 133 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 133 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679253028", "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": "1679263034" }, "total": 10005.825190888001, "count": 1, "self": 0.4898233599997184, "children": { "run_training.setup": { "total": 0.11069541300003038, "count": 1, "self": 0.11069541300003038 }, "TrainerController.start_learning": { "total": 10005.224672115, "count": 1, "self": 5.6769047892521485, "children": { "TrainerController._reset_env": { "total": 9.626390712999864, "count": 1, "self": 9.626390712999864 }, "TrainerController.advance": { "total": 9989.794200646747, "count": 260775, "self": 6.241788951574563, "children": { "env_step": { "total": 7385.649153695719, "count": 260775, "self": 6917.248764563883, "children": { "SubprocessEnvManager._take_step": { "total": 464.79865572595986, "count": 260775, "self": 19.925174743906837, "children": { "TorchPolicy.evaluate": { "total": 444.873480982053, "count": 250068, "self": 444.873480982053 } } }, "workers": { "total": 3.6017334058760753, "count": 260775, "self": 0.0, "children": { "worker_root": { "total": 9983.156414065143, "count": 260775, "is_parallel": true, "self": 3560.4724969415, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005748461999928622, "count": 1, "is_parallel": true, "self": 0.004054971000414298, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016934909995143244, "count": 8, "is_parallel": true, "self": 0.0016934909995143244 } } }, "UnityEnvironment.step": { "total": 0.08650773199997275, "count": 1, "is_parallel": true, "self": 0.007741696999801206, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005651660001149139, "count": 1, "is_parallel": true, "self": 0.0005651660001149139 }, "communicator.exchange": { "total": 0.07124664699995265, "count": 1, "is_parallel": true, "self": 0.07124664699995265 }, "steps_from_proto": { "total": 0.006954222000103982, "count": 1, "is_parallel": true, "self": 0.0055478689996562025, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014063530004477798, "count": 8, "is_parallel": true, "self": 0.0014063530004477798 } } } } } } }, "UnityEnvironment.step": { "total": 6422.6839171236425, "count": 260774, "is_parallel": true, "self": 131.17371874443143, "children": { "UnityEnvironment._generate_step_input": { "total": 98.37765279590826, "count": 260774, "is_parallel": true, "self": 98.37765279590826 }, "communicator.exchange": { "total": 5791.193611466151, "count": 260774, "is_parallel": true, "self": 5791.193611466151 }, "steps_from_proto": { "total": 401.9389341171518, "count": 260774, "is_parallel": true, "self": 87.16878858186487, "children": { "_process_rank_one_or_two_observation": { "total": 314.77014553528693, "count": 2086192, "is_parallel": true, "self": 314.77014553528693 } } } } } } } } } } }, "trainer_advance": { "total": 2597.903257999454, "count": 260775, "self": 11.436648743150272, "children": { "process_trajectory": { "total": 511.5823235022924, "count": 260775, "self": 510.488261495291, "children": { "RLTrainer._checkpoint": { "total": 1.094062007001412, "count": 8, "self": 1.094062007001412 } } }, "_update_policy": { "total": 2074.884285754011, "count": 1871, "self": 1280.9046262579282, "children": { "TorchPPOOptimizer.update": { "total": 793.9796594960831, "count": 91131, "self": 793.9796594960831 } } } } } } }, "trainer_threads": { "total": 1.227001121151261e-06, "count": 1, "self": 1.227001121151261e-06 }, "TrainerController._save_models": { "total": 0.127174739000111, "count": 1, "self": 0.0021520720001717564, "children": { "RLTrainer._checkpoint": { "total": 0.12502266699993925, "count": 1, "self": 0.12502266699993925 } } } } } } }