{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4722992777824402, "min": 0.4518720209598541, "max": 1.1943742036819458, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14100.966796875, "min": 13592.310546875, "max": 36232.53515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29921.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29921.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4628978371620178, "min": -0.099814273416996, "max": 0.4628978371620178, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 124.51951599121094, "min": -23.955425262451172, "max": 124.51951599121094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.07391109317541122, "min": -0.07391109317541122, "max": 0.5676652193069458, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -19.882083892822266, "min": -19.882083892822266, "max": 134.53665161132812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06895222530528414, "min": 0.0648202175733549, "max": 0.07500431074811234, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.965331154273978, "min": 0.5113810521313632, "max": 1.0648740307951812, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017083963290912964, "min": 0.0006223020483548624, "max": 0.024025480190671404, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2391754860727815, "min": 0.00808992662861321, "max": 0.2512727147162271, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.677718869364278e-06, "min": 7.677718869364278e-06, "max": 0.00029523424444572854, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001074880641710999, "min": 0.0001074880641710999, "max": 0.0033818303727233, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10511841428571429, "min": 0.10511841428571429, "max": 0.2968228285714286, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4716578, "min": 1.4716578, "max": 3.6545533999999993, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002656647935714284, "min": 0.0002656647935714284, "max": 0.009841300287142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003719307109999997, "min": 0.003719307109999997, "max": 0.11275494232999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01055097859352827, "min": 0.01055097859352827, "max": 0.6810292601585388, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14771370589733124, "min": 0.14771370589733124, "max": 4.767204761505127, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 390.3376623376623, "min": 390.3376623376623, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30056.0, "min": 16720.0, "max": 33661.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4797662132746214, "min": -0.9999750521965325, "max": 1.4797662132746214, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.94199842214584, "min": -31.99920167028904, "max": 113.94199842214584, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4797662132746214, "min": -0.9999750521965325, "max": 1.4797662132746214, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.94199842214584, "min": -31.99920167028904, "max": 113.94199842214584, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0427392762485633, "min": 0.0427392762485633, "max": 15.51328053895165, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2909242711393745, "min": 3.2909242711393745, "max": 263.72576916217804, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711063982", "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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711066278" }, "total": 2295.14439663, "count": 1, "self": 0.49688548599942806, "children": { "run_training.setup": { "total": 0.05607080300001144, "count": 1, "self": 0.05607080300001144 }, "TrainerController.start_learning": { "total": 2294.591440341, "count": 1, "self": 1.680361676001212, "children": { "TrainerController._reset_env": { "total": 2.8922807600000056, "count": 1, "self": 2.8922807600000056 }, "TrainerController.advance": { "total": 2289.9321220169986, "count": 63572, "self": 1.7074189160230162, "children": { "env_step": { "total": 1642.5053709379954, "count": 63572, "self": 1491.9019391429656, "children": { "SubprocessEnvManager._take_step": { "total": 149.6080896240348, "count": 63572, "self": 5.239106249005999, "children": { "TorchPolicy.evaluate": { "total": 144.3689833750288, "count": 62559, "self": 144.3689833750288 } } }, "workers": { "total": 0.9953421709950021, "count": 63572, "self": 0.0, "children": { "worker_root": { "total": 2288.9972594519863, "count": 63572, "is_parallel": true, "self": 933.6725228059995, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0047481449999509096, "count": 1, "is_parallel": true, "self": 0.003213197999912154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015349470000387555, "count": 8, "is_parallel": true, "self": 0.0015349470000387555 } } }, "UnityEnvironment.step": { "total": 0.05093311199999562, "count": 1, "is_parallel": true, "self": 0.0009386790000576184, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006180419999850528, "count": 1, "is_parallel": true, "self": 0.0006180419999850528 }, "communicator.exchange": { "total": 0.04749831099996982, "count": 1, "is_parallel": true, "self": 0.04749831099996982 }, "steps_from_proto": { "total": 0.0018780799999831288, "count": 1, "is_parallel": true, "self": 0.00045381699999325065, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014242629999898782, "count": 8, "is_parallel": true, "self": 0.0014242629999898782 } } } } } } }, "UnityEnvironment.step": { "total": 1355.3247366459868, "count": 63571, "is_parallel": true, "self": 37.50795459900405, "children": { "UnityEnvironment._generate_step_input": { "total": 26.368686636002508, "count": 63571, "is_parallel": true, "self": 26.368686636002508 }, "communicator.exchange": { "total": 1179.888430502999, "count": 63571, "is_parallel": true, "self": 1179.888430502999 }, "steps_from_proto": { "total": 111.55966490798147, "count": 63571, "is_parallel": true, "self": 23.799951081921563, "children": { "_process_rank_one_or_two_observation": { "total": 87.75971382605991, "count": 508568, "is_parallel": true, "self": 87.75971382605991 } } } } } } } } } } }, "trainer_advance": { "total": 645.7193321629802, "count": 63572, "self": 3.0856987060503798, "children": { "process_trajectory": { "total": 134.0878120139314, "count": 63572, "self": 133.8090005579313, "children": { "RLTrainer._checkpoint": { "total": 0.27881145600008495, "count": 2, "self": 0.27881145600008495 } } }, "_update_policy": { "total": 508.5458214429985, "count": 445, "self": 298.72617027102103, "children": { "TorchPPOOptimizer.update": { "total": 209.81965117197745, "count": 22812, "self": 209.81965117197745 } } } } } } }, "trainer_threads": { "total": 1.154000074166106e-06, "count": 1, "self": 1.154000074166106e-06 }, "TrainerController._save_models": { "total": 0.0866747340000984, "count": 1, "self": 0.0016815180001685803, "children": { "RLTrainer._checkpoint": { "total": 0.08499321599992982, "count": 1, "self": 0.08499321599992982 } } } } } } }