{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39735525846481323, "min": 0.39735525846481323, "max": 1.50407075881958, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11907.9423828125, "min": 11907.9423828125, "max": 45627.4921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4946378469467163, "min": -0.09572626650333405, "max": 0.5385104417800903, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 136.02540588378906, "min": -23.070030212402344, "max": 151.94345092773438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02183154970407486, "min": -0.010368878953158855, "max": 0.21013201773166656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.003676414489746, "min": -2.8929171562194824, "max": 50.641815185546875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0676496870506699, "min": 0.06645040221733081, "max": 0.07332650590341037, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9470956187093785, "min": 0.5132855413238726, "max": 1.055737317772582, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016812932809573668, "min": 0.0005237697784477002, "max": 0.01749297555686687, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23538105933403133, "min": 0.007332776898267802, "max": 0.24490165779613615, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.265454721071428e-06, "min": 7.265454721071428e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010171636609499999, "min": 0.00010171636609499999, "max": 0.0035078582307139995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242178571428572, "min": 0.10242178571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.433905, "min": 1.3886848, "max": 2.569286, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025193639285714283, "min": 0.00025193639285714283, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035271095, "min": 0.0035271095, "max": 0.11695167139999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011248973198235035, "min": 0.010679520666599274, "max": 0.3303379416465759, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15748561918735504, "min": 0.14951328933238983, "max": 2.3123655319213867, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 371.26582278481015, "min": 328.7173913043478, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29330.0, "min": 15984.0, "max": 33513.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5854794748891623, "min": -1.0000000521540642, "max": 1.6060434590377237, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.66739904135466, "min": -30.9918015897274, "max": 147.75599823147058, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5854794748891623, "min": -1.0000000521540642, "max": 1.6060434590377237, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.66739904135466, "min": -30.9918015897274, "max": 147.75599823147058, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04176631403535607, "min": 0.03606182636481801, "max": 6.430458582006395, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2577724947577735, "min": 3.2577724947577735, "max": 102.88733731210232, "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": "1675974169", "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", "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": "1675976671" }, "total": 2501.2542547250005, "count": 1, "self": 0.5391686049997588, "children": { "run_training.setup": { "total": 0.1109246260002692, "count": 1, "self": 0.1109246260002692 }, "TrainerController.start_learning": { "total": 2500.6041614940004, "count": 1, "self": 1.8529126169951269, "children": { "TrainerController._reset_env": { "total": 6.728343421000318, "count": 1, "self": 6.728343421000318 }, "TrainerController.advance": { "total": 2491.9304297780054, "count": 63761, "self": 1.9303469729338758, "children": { "env_step": { "total": 1714.29135566295, "count": 63761, "self": 1575.7081525921649, "children": { "SubprocessEnvManager._take_step": { "total": 137.42260594187337, "count": 63761, "self": 5.316583687811544, "children": { "TorchPolicy.evaluate": { "total": 132.10602225406183, "count": 62547, "self": 44.49747605908124, "children": { "TorchPolicy.sample_actions": { "total": 87.60854619498059, "count": 62547, "self": 87.60854619498059 } } } } }, "workers": { "total": 1.1605971289118315, "count": 63761, "self": 0.0, "children": { "worker_root": { "total": 2493.9793695909766, "count": 63761, "is_parallel": true, "self": 1055.6009553809372, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018289820000063628, "count": 1, "is_parallel": true, "self": 0.0006470880025517545, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011818939974546083, "count": 8, "is_parallel": true, "self": 0.0011818939974546083 } } }, "UnityEnvironment.step": { "total": 0.06751117000021623, "count": 1, "is_parallel": true, "self": 0.0005300299999362323, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004370360002212692, "count": 1, "is_parallel": true, "self": 0.0004370360002212692 }, "communicator.exchange": { "total": 0.06474566399992909, "count": 1, "is_parallel": true, "self": 0.06474566399992909 }, "steps_from_proto": { "total": 0.0017984400001296308, "count": 1, "is_parallel": true, "self": 0.0004266119995008921, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013718280006287387, "count": 8, "is_parallel": true, "self": 0.0013718280006287387 } } } } } } }, "UnityEnvironment.step": { "total": 1438.3784142100394, "count": 63760, "is_parallel": true, "self": 34.68690410000818, "children": { "UnityEnvironment._generate_step_input": { "total": 24.621843113101022, "count": 63760, "is_parallel": true, "self": 24.621843113101022 }, "communicator.exchange": { "total": 1265.042612011951, "count": 63760, "is_parallel": true, "self": 1265.042612011951 }, "steps_from_proto": { "total": 114.02705498497926, "count": 63760, "is_parallel": true, "self": 26.07910218197685, "children": { "_process_rank_one_or_two_observation": { "total": 87.94795280300241, "count": 510080, "is_parallel": true, "self": 87.94795280300241 } } } } } } } } } } }, "trainer_advance": { "total": 775.7087271421215, "count": 63761, "self": 3.5814027671540316, "children": { "process_trajectory": { "total": 172.47883647695835, "count": 63761, "self": 172.08617952095847, "children": { "RLTrainer._checkpoint": { "total": 0.3926569559998825, "count": 2, "self": 0.3926569559998825 } } }, "_update_policy": { "total": 599.6484878980091, "count": 448, "self": 228.6945369970681, "children": { "TorchPPOOptimizer.update": { "total": 370.953950900941, "count": 22752, "self": 370.953950900941 } } } } } } }, "trainer_threads": { "total": 7.680000635446049e-07, "count": 1, "self": 7.680000635446049e-07 }, "TrainerController._save_models": { "total": 0.09247490999950969, "count": 1, "self": 0.0018968479989780462, "children": { "RLTrainer._checkpoint": { "total": 0.09057806200053165, "count": 1, "self": 0.09057806200053165 } } } } } } }