{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1700698733329773, "min": 0.15845796465873718, "max": 0.26031944155693054, "count": 28 }, "Pyramids.Policy.Entropy.sum": { "value": 5161.9609375, "min": 1016.287109375, "max": 7826.34375, "count": 28 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 207.768115942029, "min": 175.07692307692307, "max": 271.4117647058824, "count": 28 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28672.0, "min": 2276.0, "max": 32298.0, "count": 28 }, "Pyramids.Step.mean": { "value": 2489948.0, "min": 1679960.0, "max": 2489948.0, "count": 28 }, "Pyramids.Step.sum": { "value": 2489948.0, "min": 1679960.0, "max": 2489948.0, "count": 28 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.9037383794784546, "min": 0.6263155341148376, "max": 0.9037383794784546, "count": 28 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 273.8327331542969, "min": 17.536834716796875, "max": 273.8327331542969, "count": 28 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0044550965540111065, "min": -0.002209288766607642, "max": 0.046209245920181274, "count": 28 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3498942852020264, "min": -0.6451123356819153, "max": 13.90898323059082, "count": 28 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7777376668392748, "min": 1.6613411556522386, "max": 1.8249230568225567, "count": 28 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 245.32779802381992, "min": 23.723999738693237, "max": 252.7247984930873, "count": 28 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7777376668392748, "min": 1.6613411556522386, "max": 1.8249230568225567, "count": 28 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 245.32779802381992, "min": 23.723999738693237, "max": 252.7247984930873, "count": 28 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011585179078858768, "min": 0.011585179078858768, "max": 0.01712447010917674, "count": 28 }, "Pyramids.Policy.RndReward.sum": { "value": 1.59875471288251, "min": 0.16541378060355783, "max": 2.061749845990562, "count": 28 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06791332284670457, "min": 0.06540743341627538, "max": 0.0716755648241988, "count": 28 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.950786519853864, "min": 0.06915688141210315, "max": 1.0671006890382462, "count": 28 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012159144297280971, "min": 0.011192417538647229, "max": 0.01619531853343471, "count": 28 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17022802016193359, "min": 0.011192417538647229, "max": 0.23043314945243767, "count": 28 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.244986108816905e-05, "min": 5.244986108816905e-05, "max": 0.0001321056559648, "count": 28 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0007342980552343667, "min": 0.0001321056559648, "max": 0.0018678535773824336, "count": 28 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11748325952380953, "min": 0.11748325952380953, "max": 0.1440352, "count": 28 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.6447656333333334, "min": 0.1440352, "max": 2.1226175666666665, "count": 28 }, "Pyramids.Policy.Beta.mean": { "value": 0.0017565776264285714, "min": 0.0017565776264285714, "max": 0.004409116479999999, "count": 28 }, "Pyramids.Policy.Beta.sum": { "value": 0.02459208677, "min": 0.004409116479999999, "max": 0.062349494910000004, "count": 28 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005485209170728922, "min": 0.005394092295318842, "max": 0.006814947817474604, "count": 28 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07679292559623718, "min": 0.006814947817474604, "max": 0.09431394934654236, "count": 28 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 28 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 28 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1752607676", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752611128" }, "total": 3452.413145898001, "count": 1, "self": 1.141851158999998, "children": { "run_training.setup": { "total": 0.04782425800112833, "count": 1, "self": 0.04782425800112833 }, "TrainerController.start_learning": { "total": 3451.223470481, "count": 1, "self": 2.3732128570936766, "children": { "TrainerController._reset_env": { "total": 3.8553263949997927, "count": 1, "self": 3.8553263949997927 }, "TrainerController.advance": { "total": 3444.985487246906, "count": 54374, "self": 2.6153873088951514, "children": { "env_step": { "total": 2473.174419440069, "count": 54374, "self": 2323.5796925855357, "children": { "SubprocessEnvManager._take_step": { "total": 148.17614540590876, "count": 54374, "self": 6.909613850857568, "children": { "TorchPolicy.evaluate": { "total": 141.2665315550512, "count": 51630, "self": 141.2665315550512 } } }, "workers": { "total": 1.4185814486245363, "count": 54374, "self": 0.0, "children": { "worker_root": { "total": 3442.0139552039436, "count": 54374, "is_parallel": true, "self": 1292.3154535910217, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032977760001813294, "count": 1, "is_parallel": true, "self": 0.0009555380001984304, "children": { "_process_rank_one_or_two_observation": { "total": 0.002342237999982899, "count": 8, "is_parallel": true, "self": 0.002342237999982899 } } }, "UnityEnvironment.step": { "total": 0.07654789699881803, "count": 1, "is_parallel": true, "self": 0.0007555769989266992, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006237380002858117, "count": 1, "is_parallel": true, "self": 0.0006237380002858117 }, "communicator.exchange": { "total": 0.07307490799939842, "count": 1, "is_parallel": true, "self": 0.07307490799939842 }, "steps_from_proto": { "total": 0.002093674000207102, "count": 1, "is_parallel": true, "self": 0.0004639890030375682, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016296849971695337, "count": 8, "is_parallel": true, "self": 0.0016296849971695337 } } } } } } }, "UnityEnvironment.step": { "total": 2149.698501612922, "count": 54373, "is_parallel": true, "self": 41.98684660366598, "children": { "UnityEnvironment._generate_step_input": { "total": 28.251620290124265, "count": 54373, "is_parallel": true, "self": 28.251620290124265 }, "communicator.exchange": { "total": 1962.164245098813, "count": 54373, "is_parallel": true, "self": 1962.164245098813 }, "steps_from_proto": { "total": 117.29578962031883, "count": 54373, "is_parallel": true, "self": 26.28809506757716, "children": { "_process_rank_one_or_two_observation": { "total": 91.00769455274167, "count": 434984, "is_parallel": true, "self": 91.00769455274167 } } } } } } } } } } }, "trainer_advance": { "total": 969.1956804979418, "count": 54374, "self": 5.1387520592816145, "children": { "process_trajectory": { "total": 159.55085079067612, "count": 54374, "self": 159.33494666267688, "children": { "RLTrainer._checkpoint": { "total": 0.21590412799923797, "count": 2, "self": 0.21590412799923797 } } }, "_update_policy": { "total": 804.5060776479841, "count": 390, "self": 317.23073637292146, "children": { "TorchPPOOptimizer.update": { "total": 487.2753412750626, "count": 18758, "self": 487.2753412750626 } } } } } } }, "trainer_threads": { "total": 1.8539994925959036e-06, "count": 1, "self": 1.8539994925959036e-06 }, "TrainerController._save_models": { "total": 0.009442128000955563, "count": 1, "self": 6.396600110747386e-05, "children": { "RLTrainer._checkpoint": { "total": 0.00937816199984809, "count": 1, "self": 0.00937816199984809 } } } } } } }