{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.24701941013336182, "min": 0.22370147705078125, "max": 0.34114405512809753, "count": 22 }, "Pyramids.Policy.Entropy.sum": { "value": 7398.7255859375, "min": 6718.20263671875, "max": 10327.11328125, "count": 22 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 245.140625, "min": 245.140625, "max": 327.10526315789474, "count": 22 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31378.0, "min": 17514.0, "max": 31697.0, "count": 22 }, "Pyramids.Step.mean": { "value": 1649913.0, "min": 1019918.0, "max": 1649913.0, "count": 22 }, "Pyramids.Step.sum": { "value": 1649913.0, "min": 1019918.0, "max": 1649913.0, "count": 22 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8134933114051819, "min": 0.5966002345085144, "max": 0.8134933114051819, "count": 22 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 237.5400390625, "min": 128.40707397460938, "max": 237.5400390625, "count": 22 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.010810206644237041, "min": -0.010810206644237041, "max": 0.02211012877523899, "count": 22 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.1565804481506348, "min": -3.1565804481506348, "max": 6.235056400299072, "count": 22 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7241364187279413, "min": 1.5469494552204484, "max": 1.7244504210741625, "count": 22 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 222.41359801590443, "min": 114.48539961874485, "max": 222.41359801590443, "count": 22 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7241364187279413, "min": 1.5469494552204484, "max": 1.7244504210741625, "count": 22 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 222.41359801590443, "min": 114.48539961874485, "max": 222.41359801590443, "count": 22 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02222682206696098, "min": 0.02222682206696098, "max": 0.033547179050153565, "count": 22 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8672600466379663, "min": 1.6793347745988285, "max": 3.316833586024586, "count": 22 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07097127216761959, "min": 0.06550184718696941, "max": 0.0729533370778275, "count": 22 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9935978103466742, "min": 0.6187000768487434, "max": 1.0943000561674125, "count": 22 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014025119535978141, "min": 0.01275076393808593, "max": 0.016184358942296563, "count": 22 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19635167350369398, "min": 0.142480781422266, "max": 0.24276538413444845, "count": 22 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00013652466877750956, "min": 0.00013652466877750956, "max": 0.00019894063368646668, "count": 22 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.001911345362885134, "min": 0.0017904657031782001, "max": 0.0027679143773620667, "count": 22 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14550820476190476, "min": 0.14550820476190476, "max": 0.16631353333333332, "count": 22 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0371148666666667, "min": 1.4968218, "max": 2.422637933333333, "count": 22 }, "Pyramids.Policy.Beta.mean": { "value": 0.004556269655714285, "min": 0.004556269655714285, "max": 0.00663472198, "count": 22 }, "Pyramids.Policy.Beta.sum": { "value": 0.06378777517999999, "min": 0.05971249782, "max": 0.09232152953999999, "count": 22 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008655091747641563, "min": 0.008655091747641563, "max": 0.010226244106888771, "count": 22 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12117128074169159, "min": 0.08283895254135132, "max": 0.15339365601539612, "count": 22 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 22 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 22 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719039194", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719040852" }, "total": 1658.0656046610002, "count": 1, "self": 0.3311192339997433, "children": { "run_training.setup": { "total": 0.05588220699974045, "count": 1, "self": 0.05588220699974045 }, "TrainerController.start_learning": { "total": 1657.6786032200007, "count": 1, "self": 0.97211951002555, "children": { "TrainerController._reset_env": { "total": 2.320944727999631, "count": 1, "self": 2.320944727999631 }, "TrainerController.advance": { "total": 1654.2426297039756, "count": 43570, "self": 1.0577510939820058, "children": { "env_step": { "total": 1222.0328911869574, "count": 43570, "self": 1130.7672467770462, "children": { "SubprocessEnvManager._take_step": { "total": 90.65485426594023, "count": 43570, "self": 3.1559880768672883, "children": { "TorchPolicy.evaluate": { "total": 87.49886618907294, "count": 41715, "self": 87.49886618907294 } } }, "workers": { "total": 0.6107901439709167, "count": 43569, "self": 0.0, "children": { "worker_root": { "total": 1654.05774715205, "count": 43569, "is_parallel": true, "self": 608.3945897670465, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002053033999800391, "count": 1, "is_parallel": true, "self": 0.0006524050004372839, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014006289993631071, "count": 8, "is_parallel": true, "self": 0.0014006289993631071 } } }, "UnityEnvironment.step": { "total": 0.04781640600049286, "count": 1, "is_parallel": true, "self": 0.0006432730006054044, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004788030000781873, "count": 1, "is_parallel": true, "self": 0.0004788030000781873 }, "communicator.exchange": { "total": 0.045015523999609286, "count": 1, "is_parallel": true, "self": 0.045015523999609286 }, "steps_from_proto": { "total": 0.0016788060001999838, "count": 1, "is_parallel": true, "self": 0.00034541300101409433, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013333929991858895, "count": 8, "is_parallel": true, "self": 0.0013333929991858895 } } } } } } }, "UnityEnvironment.step": { "total": 1045.6631573850036, "count": 43568, "is_parallel": true, "self": 23.285176843111003, "children": { "UnityEnvironment._generate_step_input": { "total": 15.537738832067589, "count": 43568, "is_parallel": true, "self": 15.537738832067589 }, "communicator.exchange": { "total": 941.4118091279843, "count": 43568, "is_parallel": true, "self": 941.4118091279843 }, "steps_from_proto": { "total": 65.42843258184075, "count": 43568, "is_parallel": true, "self": 13.649580882759437, "children": { "_process_rank_one_or_two_observation": { "total": 51.778851699081315, "count": 348544, "is_parallel": true, "self": 51.778851699081315 } } } } } } } } } } }, "trainer_advance": { "total": 431.1519874230362, "count": 43569, "self": 2.00465622304273, "children": { "process_trajectory": { "total": 88.9402615469944, "count": 43569, "self": 88.73077637299411, "children": { "RLTrainer._checkpoint": { "total": 0.20948517400029232, "count": 2, "self": 0.20948517400029232 } } }, "_update_policy": { "total": 340.20706965299905, "count": 315, "self": 199.04264628404417, "children": { "TorchPPOOptimizer.update": { "total": 141.16442336895489, "count": 15153, "self": 141.16442336895489 } } } } } } }, "trainer_threads": { "total": 3.201999788871035e-06, "count": 1, "self": 3.201999788871035e-06 }, "TrainerController._save_models": { "total": 0.14290607600014482, "count": 1, "self": 0.00190373500026908, "children": { "RLTrainer._checkpoint": { "total": 0.14100234099987574, "count": 1, "self": 0.14100234099987574 } } } } } } }