{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38034588098526, "min": 0.38034588098526, "max": 1.5413641929626465, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 11367.77734375, "min": 11347.216796875, "max": 46758.82421875, "count": 66 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 66 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2366734892129898, "min": -0.1582891047000885, "max": 0.3309483528137207, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 61.29843521118164, "min": -37.51451873779297, "max": 84.7227783203125, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03656044602394104, "min": -0.25130996108055115, "max": 0.18846359848976135, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -9.469155311584473, "min": -64.83796691894531, "max": 45.23126220703125, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06788141211533609, "min": 0.06624055287809774, "max": 0.07188534102275777, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9503397696147053, "min": 0.48590444282015743, "max": 1.0506042377194664, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013564155482267127, "min": 0.00016521106460144042, "max": 0.019684321844709172, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18989817675173978, "min": 0.0016521106460144043, "max": 0.2755805058259284, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.379690397278574e-06, "min": 7.379690397278574e-06, "max": 0.00029515063018788575, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010331566556190004, "min": 0.00010331566556190004, "max": 0.0030219734926756, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024598642857143, "min": 0.1024598642857143, "max": 0.19838354285714285, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344381000000002, "min": 1.3691136000000002, "max": 2.3182248, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025574044214285717, "min": 0.00025574044214285717, "max": 0.00983851593142857, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035803661900000007, "min": 0.0035803661900000007, "max": 0.10076170756000001, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007886596024036407, "min": 0.007886596024036407, "max": 0.2885569930076599, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1104123443365097, "min": 0.1104123443365097, "max": 2.0198988914489746, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 541.3928571428571, "min": 522.7068965517242, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30318.0, "min": 15984.0, "max": 33405.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9941999682092241, "min": -1.0000000521540642, "max": 1.2358482429950401, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 55.67519821971655, "min": -32.000001668930054, "max": 71.67919809371233, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9941999682092241, "min": -1.0000000521540642, "max": 1.2358482429950401, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 55.67519821971655, "min": -32.000001668930054, "max": 71.67919809371233, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0448177528180947, "min": 0.0448177528180947, "max": 5.773372193798423, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 2.509794157813303, "min": 2.343173041634145, "max": 92.37395510077477, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678705368", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678707384" }, "total": 2016.422110788, "count": 1, "self": 0.43708135800011405, "children": { "run_training.setup": { "total": 0.11546557200006191, "count": 1, "self": 0.11546557200006191 }, "TrainerController.start_learning": { "total": 2015.869563858, "count": 1, "self": 1.315922294079428, "children": { "TrainerController._reset_env": { "total": 9.562308814000062, "count": 1, "self": 9.562308814000062 }, "TrainerController.advance": { "total": 2004.9057880509206, "count": 63335, "self": 1.4386252858851094, "children": { "env_step": { "total": 1384.6090484049892, "count": 63335, "self": 1267.8628270299666, "children": { "SubprocessEnvManager._take_step": { "total": 115.90193558099179, "count": 63335, "self": 5.301615201987147, "children": { "TorchPolicy.evaluate": { "total": 110.60032037900464, "count": 62567, "self": 110.60032037900464 } } }, "workers": { "total": 0.8442857940307249, "count": 63335, "self": 0.0, "children": { "worker_root": { "total": 2011.420638815979, "count": 63335, "is_parallel": true, "self": 859.9023666840096, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021389730000009877, "count": 1, "is_parallel": true, "self": 0.0006224389999260893, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015165340000748984, "count": 8, "is_parallel": true, "self": 0.0015165340000748984 } } }, "UnityEnvironment.step": { "total": 0.13963642999999593, "count": 1, "is_parallel": true, "self": 0.0005633030000353756, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005027539999673536, "count": 1, "is_parallel": true, "self": 0.0005027539999673536 }, "communicator.exchange": { "total": 0.1368526410000186, "count": 1, "is_parallel": true, "self": 0.1368526410000186 }, "steps_from_proto": { "total": 0.0017177319999746032, "count": 1, "is_parallel": true, "self": 0.0003710759998512003, "children": { "_process_rank_one_or_two_observation": { "total": 0.001346656000123403, "count": 8, "is_parallel": true, "self": 0.001346656000123403 } } } } } } }, "UnityEnvironment.step": { "total": 1151.5182721319693, "count": 63334, "is_parallel": true, "self": 31.54017817293129, "children": { "UnityEnvironment._generate_step_input": { "total": 24.281930373047317, "count": 63334, "is_parallel": true, "self": 24.281930373047317 }, "communicator.exchange": { "total": 999.1012235639962, "count": 63334, "is_parallel": true, "self": 999.1012235639962 }, "steps_from_proto": { "total": 96.59494002199449, "count": 63334, "is_parallel": true, "self": 20.698782020047815, "children": { "_process_rank_one_or_two_observation": { "total": 75.89615800194667, "count": 506672, "is_parallel": true, "self": 75.89615800194667 } } } } } } } } } } }, "trainer_advance": { "total": 618.8581143600462, "count": 63335, "self": 2.480860432093891, "children": { "process_trajectory": { "total": 122.46243180795034, "count": 63335, "self": 122.26027844095017, "children": { "RLTrainer._checkpoint": { "total": 0.2021533670001645, "count": 2, "self": 0.2021533670001645 } } }, "_update_policy": { "total": 493.914822120002, "count": 428, "self": 307.2833172130232, "children": { "TorchPPOOptimizer.update": { "total": 186.63150490697876, "count": 22878, "self": 186.63150490697876 } } } } } } }, "trainer_threads": { "total": 1.0710000424296595e-06, "count": 1, "self": 1.0710000424296595e-06 }, "TrainerController._save_models": { "total": 0.08554362799986848, "count": 1, "self": 0.0014075069998398249, "children": { "RLTrainer._checkpoint": { "total": 0.08413612100002865, "count": 1, "self": 0.08413612100002865 } } } } } } }