{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9817102551460266, "min": 0.9242140650749207, "max": 1.609288215637207, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 2811.6181640625, "min": 1892.7904052734375, "max": 6591.64453125, "count": 33 }, "Pyramids.Step.mean": { "value": 98911.0, "min": 2944.0, "max": 98911.0, "count": 33 }, "Pyramids.Step.sum": { "value": 98911.0, "min": 2944.0, "max": 98911.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04163406789302826, "min": -0.10635673254728317, "max": 0.11394832283258438, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -0.9575835466384888, "min": -2.5525615215301514, "max": 2.6208114624023438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1324186623096466, "min": 0.00787387229502201, "max": 0.4475221633911133, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.0456292629241943, "min": 0.1810990571975708, "max": 11.059113502502441, "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 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07580888934899122, "min": 0.05650719351993472, "max": 0.08154219802236184, "count": 29 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.07580888934899122, "min": 0.05650719351993472, "max": 0.16098307607028925, "count": 29 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00858449243241921, "min": 0.0002096855548420446, "max": 0.02114346721403611, "count": 29 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.00858449243241921, "min": 0.0002096855548420446, "max": 0.02114346721403611, "count": 29 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.0947096351000007e-05, "min": 1.0947096351000007e-05, "max": 0.00028771200409599993, "count": 29 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.0947096351000007e-05, "min": 1.0947096351000007e-05, "max": 0.00028771200409599993, "count": 29 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.103649, "min": 0.103649, "max": 0.19590400000000005, "count": 29 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.103649, "min": 0.103649, "max": 0.27723200000000003, "count": 29 }, "Pyramids.Policy.Beta.mean": { "value": 0.00037453510000000026, "min": 0.00037453510000000026, "max": 0.0095908096, "count": 29 }, "Pyramids.Policy.Beta.sum": { "value": 0.00037453510000000026, "min": 0.00037453510000000026, "max": 0.0095908096, "count": 29 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.11507463455200195, "min": 0.09981845319271088, "max": 0.9768047332763672, "count": 29 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11507463455200195, "min": 0.09981845319271088, "max": 0.9768047332763672, "count": 29 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 990.9230769230769, "min": 181.0, "max": 999.0, "count": 13 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 12882.0, "min": 181.0, "max": 15984.0, "count": 13 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.105999916791916, "min": -1.0000000521540642, "max": 1.819000020623207, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 1.105999916791916, "min": -16.000000834465027, "max": 1.819000020623207, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.105999916791916, "min": -1.0000000521540642, "max": 1.819000020623207, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 1.105999916791916, "min": -16.000000834465027, "max": 1.819000020623207, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 1.1296864300966263, "min": 0.373375728726387, "max": 9.273354778687159, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 1.1296864300966263, "min": 0.373375728726387, "max": 82.790895819664, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676490843", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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=Pyramids Training --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676491053" }, "total": 210.45567824699992, "count": 1, "self": 0.47598377200006325, "children": { "run_training.setup": { "total": 0.10828723999998147, "count": 1, "self": 0.10828723999998147 }, "TrainerController.start_learning": { "total": 209.87140723499988, "count": 1, "self": 0.12007632701056536, "children": { "TrainerController._reset_env": { "total": 7.143835129999843, "count": 1, "self": 7.143835129999843 }, "TrainerController.advance": { "total": 202.5131940869892, "count": 6325, "self": 0.13459399598673372, "children": { "env_step": { "total": 129.16711768600794, "count": 6325, "self": 117.86653780600659, "children": { "SubprocessEnvManager._take_step": { "total": 11.224153669994621, "count": 6325, "self": 0.44416318500839225, "children": { "TorchPolicy.evaluate": { "total": 10.779990484986229, "count": 6315, "self": 3.592520562971913, "children": { "TorchPolicy.sample_actions": { "total": 7.187469922014316, "count": 6315, "self": 7.187469922014316 } } } } }, "workers": { "total": 0.07642621000672989, "count": 6325, "self": 0.0, "children": { "worker_root": { "total": 209.4020740189976, "count": 6325, "is_parallel": true, "self": 102.3103011930009, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019784199998866825, "count": 1, "is_parallel": true, "self": 0.0006531299998187023, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013252900000679801, "count": 8, "is_parallel": true, "self": 0.0013252900000679801 } } }, "UnityEnvironment.step": { "total": 0.07714149899993572, "count": 1, "is_parallel": true, "self": 0.0005538119999073388, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004960509997999907, "count": 1, "is_parallel": true, "self": 0.0004960509997999907 }, "communicator.exchange": { "total": 0.07448717300007957, "count": 1, "is_parallel": true, "self": 0.07448717300007957 }, "steps_from_proto": { "total": 0.0016044630001488258, "count": 1, "is_parallel": true, "self": 0.0004050429997732863, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011994200003755395, "count": 8, "is_parallel": true, "self": 0.0011994200003755395 } } } } } } }, "UnityEnvironment.step": { "total": 107.09177282599671, "count": 6324, "is_parallel": true, "self": 3.1052252909923936, "children": { "UnityEnvironment._generate_step_input": { "total": 2.253295205004406, "count": 6324, "is_parallel": true, "self": 2.253295205004406 }, "communicator.exchange": { "total": 91.96426635999933, "count": 6324, "is_parallel": true, "self": 91.96426635999933 }, "steps_from_proto": { "total": 9.768985970000585, "count": 6324, "is_parallel": true, "self": 2.173376013968209, "children": { "_process_rank_one_or_two_observation": { "total": 7.595609956032376, "count": 50592, "is_parallel": true, "self": 7.595609956032376 } } } } } } } } } } }, "trainer_advance": { "total": 73.21148240499451, "count": 6325, "self": 0.16400113199370026, "children": { "process_trajectory": { "total": 15.68313147300114, "count": 6325, "self": 15.68313147300114 }, "_update_policy": { "total": 57.36434979999967, "count": 32, "self": 21.891281722002986, "children": { "TorchPPOOptimizer.update": { "total": 35.473068077996686, "count": 2322, "self": 35.473068077996686 } } } } } } }, "trainer_threads": { "total": 1.018000148178544e-06, "count": 1, "self": 1.018000148178544e-06 }, "TrainerController._save_models": { "total": 0.09430067300013434, "count": 1, "self": 0.001461332000189941, "children": { "RLTrainer._checkpoint": { "total": 0.0928393409999444, "count": 1, "self": 0.0928393409999444 } } } } } } }