{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.353591650724411, "min": 0.34824860095977783, "max": 1.460567593574524, "count": 56 }, "Pyramids.Policy.Entropy.sum": { "value": 10624.7216796875, "min": 10402.8818359375, "max": 44307.77734375, "count": 56 }, "Pyramids.Step.mean": { "value": 1679936.0, "min": 29952.0, "max": 1679936.0, "count": 56 }, "Pyramids.Step.sum": { "value": 1679936.0, "min": 29952.0, "max": 1679936.0, "count": 56 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6895836591720581, "min": -0.11628881096839905, "max": 0.767508864402771, "count": 56 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 195.84176635742188, "min": -27.90931510925293, "max": 221.81005859375, "count": 56 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012621568515896797, "min": -0.031149884685873985, "max": 0.23430316150188446, "count": 56 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.5845253467559814, "min": -8.53506851196289, "max": 55.529850006103516, "count": 56 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0687060652755045, "min": 0.06586742103986797, "max": 0.07400308160382943, "count": 56 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.961884913857063, "min": 0.4948795660386857, "max": 1.0948977358365322, "count": 56 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01424026587008367, "min": 0.0006663407392315117, "max": 0.016218521269740233, "count": 56 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19936372218117138, "min": 0.008662429610009651, "max": 0.22705929777636327, "count": 56 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00025002954379968137, "min": 0.00025002954379968137, "max": 0.0002995150630187886, "count": 56 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0035004136131955394, "min": 0.00209660544113152, "max": 0.004169216960261049, "count": 56 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.18334317571428568, "min": 0.18334317571428568, "max": 0.1998383542857143, "count": 56 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.5668044599999997, "min": 1.3988684800000002, "max": 2.889738950000001, "count": 56 }, "Pyramids.Policy.Beta.mean": { "value": 0.008335983253857144, "min": 0.008335983253857144, "max": 0.009983851593142858, "count": 56 }, "Pyramids.Policy.Beta.sum": { "value": 0.116703765554, "min": 0.06988696115200001, "max": 0.138984921105, "count": 56 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00815605092793703, "min": 0.007685383781790733, "max": 0.36510565876960754, "count": 56 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11418470740318298, "min": 0.11103454977273941, "max": 2.555739641189575, "count": 56 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 291.18446601941747, "min": 257.77777777777777, "max": 999.0, "count": 56 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29992.0, "min": 15984.0, "max": 32982.0, "count": 56 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6707115229219198, "min": -1.0000000521540642, "max": 1.7251264798080819, "count": 56 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 173.75399838387966, "min": -30.49400170147419, "max": 201.83979813754559, "count": 56 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6707115229219198, "min": -1.0000000521540642, "max": 1.7251264798080819, "count": 56 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 173.75399838387966, "min": -30.49400170147419, "max": 201.83979813754559, "count": 56 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024493022927624855, "min": 0.02134973293756887, "max": 7.382361877709627, "count": 56 }, "Pyramids.Policy.RndReward.sum": { "value": 2.547274384472985, "min": 2.2203722255071625, "max": 118.11779004335403, "count": 56 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 56 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 56 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693823363", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1693827061" }, "total": 3698.533238058, "count": 1, "self": 0.5815155339992089, "children": { "run_training.setup": { "total": 0.0405830300001071, "count": 1, "self": 0.0405830300001071 }, "TrainerController.start_learning": { "total": 3697.9111394940005, "count": 1, "self": 2.180277634005506, "children": { "TrainerController._reset_env": { "total": 4.018690837000122, "count": 1, "self": 4.018690837000122 }, "TrainerController.advance": { "total": 3691.415373041995, "count": 107607, "self": 2.2184552468925176, "children": { "env_step": { "total": 2596.8048594829415, "count": 107607, "self": 2419.117078891062, "children": { "SubprocessEnvManager._take_step": { "total": 176.33687775006547, "count": 107607, "self": 7.782326285007912, "children": { "TorchPolicy.evaluate": { "total": 168.55455146505756, "count": 105184, "self": 168.55455146505756 } } }, "workers": { "total": 1.3509028418138769, "count": 107607, "self": 0.0, "children": { "worker_root": { "total": 3689.944686289052, "count": 107607, "is_parallel": true, "self": 1457.3822174250977, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017570739998973295, "count": 1, "is_parallel": true, "self": 0.0005461169998852711, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012109570000120584, "count": 8, "is_parallel": true, "self": 0.0012109570000120584 } } }, "UnityEnvironment.step": { "total": 0.04616919499994765, "count": 1, "is_parallel": true, "self": 0.0005645289998028602, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004904840000108379, "count": 1, "is_parallel": true, "self": 0.0004904840000108379 }, "communicator.exchange": { "total": 0.04298331400013922, "count": 1, "is_parallel": true, "self": 0.04298331400013922 }, "steps_from_proto": { "total": 0.0021308679999947344, "count": 1, "is_parallel": true, "self": 0.0005569869999817456, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015738810000129888, "count": 8, "is_parallel": true, "self": 0.0015738810000129888 } } } } } } }, "UnityEnvironment.step": { "total": 2232.562468863954, "count": 107606, "is_parallel": true, "self": 56.06648272397479, "children": { "UnityEnvironment._generate_step_input": { "total": 37.790391623057985, "count": 107606, "is_parallel": true, "self": 37.790391623057985 }, "communicator.exchange": { "total": 1965.960767741927, "count": 107606, "is_parallel": true, "self": 1965.960767741927 }, "steps_from_proto": { "total": 172.7448267749944, "count": 107606, "is_parallel": true, "self": 33.357563551233625, "children": { "_process_rank_one_or_two_observation": { "total": 139.38726322376078, "count": 860848, "is_parallel": true, "self": 139.38726322376078 } } } } } } } } } } }, "trainer_advance": { "total": 1092.3920583121605, "count": 107607, "self": 4.301352635175817, "children": { "process_trajectory": { "total": 183.98929780698995, "count": 107607, "self": 183.68874121799013, "children": { "RLTrainer._checkpoint": { "total": 0.3005565889998252, "count": 3, "self": 0.3005565889998252 } } }, "_update_policy": { "total": 904.1014078699948, "count": 771, "self": 587.1496411399585, "children": { "TorchPPOOptimizer.update": { "total": 316.9517667300363, "count": 38373, "self": 316.9517667300363 } } } } } } }, "trainer_threads": { "total": 1.282999619434122e-06, "count": 1, "self": 1.282999619434122e-06 }, "TrainerController._save_models": { "total": 0.29679669800043484, "count": 1, "self": 0.0039019360001475434, "children": { "RLTrainer._checkpoint": { "total": 0.2928947620002873, "count": 1, "self": 0.2928947620002873 } } } } } } }