{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48065105080604553, "min": 0.4798978269100189, "max": 1.1220625638961792, "count": 29 }, "Pyramids.Policy.Entropy.sum": { "value": 14388.76953125, "min": 14212.654296875, "max": 34110.703125, "count": 29 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 149995.0, "max": 989948.0, "count": 29 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 149995.0, "max": 989948.0, "count": 29 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5064566731452942, "min": -0.07418560981750488, "max": 0.5412768125534058, "count": 29 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.22393798828125, "min": -17.952917098999023, "max": 147.227294921875, "count": 29 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03052312135696411, "min": -0.001319264993071556, "max": 0.06609056890010834, "count": 29 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.149673461914062, "min": -0.33113551139831543, "max": 13.795373916625977, "count": 29 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06964786789224793, "min": 0.06426054523977012, "max": 0.07468332773012172, "count": 29 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9750701504914709, "min": 0.3520741780367465, "max": 1.071499333552578, "count": 29 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014746138068620072, "min": 0.00017284317698471275, "max": 0.015604803865634105, "count": 29 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.206445932960681, "min": 0.0008642158849235637, "max": 0.21846725411887746, "count": 29 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.372940399528579e-06, "min": 7.372940399528579e-06, "max": 0.00025742839419054, "count": 29 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010322116559340011, "min": 0.00010322116559340011, "max": 0.0032525979158008005, "count": 29 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245761428571429, "min": 0.10245761428571429, "max": 0.18580946000000004, "count": 29 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344066, "min": 0.9290473000000002, "max": 2.5275625000000006, "count": 29 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002555156671428574, "min": 0.0002555156671428574, "max": 0.008582365054000002, "count": 29 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035772193400000034, "min": 0.0035772193400000034, "max": 0.10845150007999999, "count": 29 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00785643607378006, "min": 0.00785643607378006, "max": 0.05546265095472336, "count": 29 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10999010503292084, "min": 0.10999010503292084, "max": 0.5188475847244263, "count": 29 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 397.49333333333334, "min": 361.7439024390244, "max": 999.0, "count": 29 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29812.0, "min": 15984.0, "max": 32343.0, "count": 29 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5224933087825776, "min": -1.0000000521540642, "max": 1.5406560884198037, "count": 29 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.18699815869331, "min": -22.684201456606388, "max": 126.33379925042391, "count": 29 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5224933087825776, "min": -1.0000000521540642, "max": 1.5406560884198037, "count": 29 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.18699815869331, "min": -22.684201456606388, "max": 126.33379925042391, "count": 29 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03290017237828579, "min": 0.03027044881132386, "max": 0.5963121356908232, "count": 29 }, "Pyramids.Policy.RndReward.sum": { "value": 2.467512928371434, "min": 2.3938862106733723, "max": 15.233707860810682, "count": 29 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 29 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 29 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688712922", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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=KLJan05-Pyramids-Training --no-graphics --resume", "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": "1688714875" }, "total": 1953.1778916150001, "count": 1, "self": 0.47664636300032726, "children": { "run_training.setup": { "total": 0.03846240099994702, "count": 1, "self": 0.03846240099994702 }, "TrainerController.start_learning": { "total": 1952.662782851, "count": 1, "self": 1.4037849070359698, "children": { "TrainerController._reset_env": { "total": 3.996508485999925, "count": 1, "self": 3.996508485999925 }, "TrainerController.advance": { "total": 1947.168179516964, "count": 55676, "self": 1.3236069869774383, "children": { "env_step": { "total": 1390.1448735000317, "count": 55676, "self": 1285.6247089229973, "children": { "SubprocessEnvManager._take_step": { "total": 103.69748869599846, "count": 55676, "self": 4.303733272982413, "children": { "TorchPolicy.evaluate": { "total": 99.39375542301605, "count": 54443, "self": 99.39375542301605 } } }, "workers": { "total": 0.8226758810358206, "count": 55676, "self": 0.0, "children": { "worker_root": { "total": 1947.2436838209596, "count": 55676, "is_parallel": true, "self": 767.1333403839435, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001721568999982992, "count": 1, "is_parallel": true, "self": 0.0005420090001280187, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011795599998549733, "count": 8, "is_parallel": true, "self": 0.0011795599998549733 } } }, "UnityEnvironment.step": { "total": 0.052451023999992685, "count": 1, "is_parallel": true, "self": 0.0005916090000255281, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005768480000369891, "count": 1, "is_parallel": true, "self": 0.0005768480000369891 }, "communicator.exchange": { "total": 0.04933949299993401, "count": 1, "is_parallel": true, "self": 0.04933949299993401 }, "steps_from_proto": { "total": 0.0019430739999961588, "count": 1, "is_parallel": true, "self": 0.00040355399983127427, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015395200001648846, "count": 8, "is_parallel": true, "self": 0.0015395200001648846 } } } } } } }, "UnityEnvironment.step": { "total": 1180.1103434370161, "count": 55675, "is_parallel": true, "self": 29.428543415944432, "children": { "UnityEnvironment._generate_step_input": { "total": 19.77364289504635, "count": 55675, "is_parallel": true, "self": 19.77364289504635 }, "communicator.exchange": { "total": 1041.0423267700226, "count": 55675, "is_parallel": true, "self": 1041.0423267700226 }, "steps_from_proto": { "total": 89.86583035600279, "count": 55675, "is_parallel": true, "self": 17.994584492995045, "children": { "_process_rank_one_or_two_observation": { "total": 71.87124586300774, "count": 445400, "is_parallel": true, "self": 71.87124586300774 } } } } } } } } } } }, "trainer_advance": { "total": 555.6996990299548, "count": 55676, "self": 2.6135592619712043, "children": { "process_trajectory": { "total": 94.8778441619827, "count": 55676, "self": 94.59408217598298, "children": { "RLTrainer._checkpoint": { "total": 0.2837619859997176, "count": 2, "self": 0.2837619859997176 } } }, "_update_policy": { "total": 458.2082956060009, "count": 401, "self": 289.97399806600424, "children": { "TorchPPOOptimizer.update": { "total": 168.23429753999665, "count": 19791, "self": 168.23429753999665 } } } } } } }, "trainer_threads": { "total": 1.097000222216593e-06, "count": 1, "self": 1.097000222216593e-06 }, "TrainerController._save_models": { "total": 0.09430884399989736, "count": 1, "self": 0.0016985620000014023, "children": { "RLTrainer._checkpoint": { "total": 0.09261028199989596, "count": 1, "self": 0.09261028199989596 } } } } } } }