{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39594748616218567, "min": 0.3801190257072449, "max": 1.4076942205429077, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12024.1328125, "min": 11367.0791015625, "max": 42703.8125, "count": 33 }, "Pyramids.Step.mean": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5139580368995667, "min": -0.13790540397167206, "max": 0.5511236786842346, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.7686767578125, "min": -33.23520278930664, "max": 155.4168701171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0022845836356282234, "min": -0.022786881774663925, "max": 0.5025518536567688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6168375611305237, "min": -6.0157365798950195, "max": 119.10478973388672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06716546974106072, "min": 0.06526638166307672, "max": 0.07293945225796773, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.94031657637485, "min": 0.5105761658057741, "max": 1.0344177707892788, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012353459408803334, "min": 0.000680715049517911, "max": 0.015525419622939633, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17294843172324667, "min": 0.009530010693250754, "max": 0.21735587472115486, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.648126022085718e-06, "min": 7.648126022085718e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010707376430920006, "min": 0.00010707376430920006, "max": 0.003507455630848199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254934285714287, "min": 0.10254934285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356908000000002, "min": 1.3886848, "max": 2.5691518, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026467935142857155, "min": 0.00026467935142857155, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037055109200000015, "min": 0.0037055109200000015, "max": 0.11693826482000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014019317924976349, "min": 0.014019317924976349, "max": 0.6390002369880676, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19627045094966888, "min": 0.19627045094966888, "max": 4.473001480102539, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 374.7162162162162, "min": 344.3636363636364, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27729.0, "min": 15984.0, "max": 33452.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4090053878120474, "min": -1.0000000521540642, "max": 1.6165774770081043, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.2663986980915, "min": -29.628401644527912, "max": 143.26279834657907, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4090053878120474, "min": -1.0000000521540642, "max": 1.6165774770081043, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.2663986980915, "min": -29.628401644527912, "max": 143.26279834657907, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.054473458735800874, "min": 0.05134430645148824, "max": 12.499833401292562, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.031035946449265, "min": 4.031035946449265, "max": 199.997334420681, "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": "1685040178", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1685042334" }, "total": 2156.50135813, "count": 1, "self": 0.8174747020002542, "children": { "run_training.setup": { "total": 0.03628847799996038, "count": 1, "self": 0.03628847799996038 }, "TrainerController.start_learning": { "total": 2155.64759495, "count": 1, "self": 1.375283336022676, "children": { "TrainerController._reset_env": { "total": 3.6871634710000762, "count": 1, "self": 3.6871634710000762 }, "TrainerController.advance": { "total": 2150.4870169299766, "count": 63735, "self": 1.364928163003242, "children": { "env_step": { "total": 1519.2527713319976, "count": 63735, "self": 1407.747336174077, "children": { "SubprocessEnvManager._take_step": { "total": 110.67511432693686, "count": 63735, "self": 4.825785894973478, "children": { "TorchPolicy.evaluate": { "total": 105.84932843196339, "count": 62547, "self": 105.84932843196339 } } }, "workers": { "total": 0.8303208309837373, "count": 63735, "self": 0.0, "children": { "worker_root": { "total": 2150.6074437929346, "count": 63735, "is_parallel": true, "self": 856.9305646479306, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017258200000469515, "count": 1, "is_parallel": true, "self": 0.000567506000152207, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011583139998947445, "count": 8, "is_parallel": true, "self": 0.0011583139998947445 } } }, "UnityEnvironment.step": { "total": 0.04587353199985955, "count": 1, "is_parallel": true, "self": 0.000542655999879571, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048216499999398366, "count": 1, "is_parallel": true, "self": 0.00048216499999398366 }, "communicator.exchange": { "total": 0.04302855700007058, "count": 1, "is_parallel": true, "self": 0.04302855700007058 }, "steps_from_proto": { "total": 0.0018201539999154193, "count": 1, "is_parallel": true, "self": 0.0004296909999084164, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013904630000070028, "count": 8, "is_parallel": true, "self": 0.0013904630000070028 } } } } } } }, "UnityEnvironment.step": { "total": 1293.676879145004, "count": 63734, "is_parallel": true, "self": 31.299189419022923, "children": { "UnityEnvironment._generate_step_input": { "total": 24.29726067604588, "count": 63734, "is_parallel": true, "self": 24.29726067604588 }, "communicator.exchange": { "total": 1137.6608444849367, "count": 63734, "is_parallel": true, "self": 1137.6608444849367 }, "steps_from_proto": { "total": 100.41958456499856, "count": 63734, "is_parallel": true, "self": 20.582359416961935, "children": { "_process_rank_one_or_two_observation": { "total": 79.83722514803662, "count": 509872, "is_parallel": true, "self": 79.83722514803662 } } } } } } } } } } }, "trainer_advance": { "total": 629.8693174349758, "count": 63735, "self": 2.5640535240247573, "children": { "process_trajectory": { "total": 110.61265421795247, "count": 63735, "self": 110.41272188395237, "children": { "RLTrainer._checkpoint": { "total": 0.19993233400009558, "count": 2, "self": 0.19993233400009558 } } }, "_update_policy": { "total": 516.6926096929985, "count": 450, "self": 332.1491097239741, "children": { "TorchPPOOptimizer.update": { "total": 184.54349996902442, "count": 22830, "self": 184.54349996902442 } } } } } } }, "trainer_threads": { "total": 1.2800001059076749e-06, "count": 1, "self": 1.2800001059076749e-06 }, "TrainerController._save_models": { "total": 0.09812993300056405, "count": 1, "self": 0.0014605390006181551, "children": { "RLTrainer._checkpoint": { "total": 0.0966693939999459, "count": 1, "self": 0.0966693939999459 } } } } } } }