{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3095568120479584, "min": 0.3032616674900055, "max": 1.398167371749878, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9286.7041015625, "min": 9141.51953125, "max": 42414.8046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989937.0, "min": 29952.0, "max": 989937.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989937.0, "min": 29952.0, "max": 989937.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6718105673789978, "min": -0.0989900454878807, "max": 0.6718105673789978, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 197.51231384277344, "min": -23.757610321044922, "max": 197.51231384277344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.012169343419373035, "min": -0.034034181386232376, "max": 0.340353399515152, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.577786922454834, "min": -8.88292121887207, "max": 80.66375732421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0664614228333535, "min": 0.06537212099667636, "max": 0.07339101404936736, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9304599196669491, "min": 0.4961760442671513, "max": 1.0946579658581563, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017766982927111843, "min": 0.0006795215624811844, "max": 0.017766982927111843, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2487377609795658, "min": 0.004756650937368291, "max": 0.2487377609795658, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.312811848142857e-06, "min": 7.312811848142857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010237936587399999, "min": 0.00010237936587399999, "max": 0.0033794447735185, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243757142857142, "min": 0.10243757142857142, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341259999999998, "min": 1.3691136000000002, "max": 2.5264815, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025351338571428573, "min": 0.00025351338571428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035491874000000002, "min": 0.0035491874000000002, "max": 0.11267550185, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0102896299213171, "min": 0.01018145214766264, "max": 0.4057447612285614, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1440548151731491, "min": 0.1440548151731491, "max": 2.8402132987976074, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 282.6371681415929, "min": 282.6371681415929, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31938.0, "min": 15984.0, "max": 32969.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6812803447246552, "min": -1.0000000521540642, "max": 1.6887821707837651, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 188.30339860916138, "min": -32.000001668930054, "max": 188.30339860916138, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6812803447246552, "min": -1.0000000521540642, "max": 1.6887821707837651, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 188.30339860916138, "min": -32.000001668930054, "max": 188.30339860916138, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029473348894628413, "min": 0.029473348894628413, "max": 7.22762886621058, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3010150761983823, "min": 3.181157567509217, "max": 115.64206185936928, "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": "1692192555", "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": "1692194992" }, "total": 2436.992459815, "count": 1, "self": 0.5258408330000748, "children": { "run_training.setup": { "total": 0.0404048390000753, "count": 1, "self": 0.0404048390000753 }, "TrainerController.start_learning": { "total": 2436.426214143, "count": 1, "self": 1.5273461460278668, "children": { "TrainerController._reset_env": { "total": 4.160288271999889, "count": 1, "self": 4.160288271999889 }, "TrainerController.advance": { "total": 2430.6400292709723, "count": 64203, "self": 1.5485170009023932, "children": { "env_step": { "total": 1738.9232867290466, "count": 64203, "self": 1622.211074631048, "children": { "SubprocessEnvManager._take_step": { "total": 115.77913239503141, "count": 64203, "self": 5.180402942013643, "children": { "TorchPolicy.evaluate": { "total": 110.59872945301777, "count": 62549, "self": 110.59872945301777 } } }, "workers": { "total": 0.933079702967234, "count": 64203, "self": 0.0, "children": { "worker_root": { "total": 2430.515098886929, "count": 64203, "is_parallel": true, "self": 932.6499854109318, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001753835000045001, "count": 1, "is_parallel": true, "self": 0.0005451980002817436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012086369997632573, "count": 8, "is_parallel": true, "self": 0.0012086369997632573 } } }, "UnityEnvironment.step": { "total": 0.06420976100002918, "count": 1, "is_parallel": true, "self": 0.0005740160002005723, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005153820000032283, "count": 1, "is_parallel": true, "self": 0.0005153820000032283 }, "communicator.exchange": { "total": 0.06112837099999524, "count": 1, "is_parallel": true, "self": 0.06112837099999524 }, "steps_from_proto": { "total": 0.001991991999830134, "count": 1, "is_parallel": true, "self": 0.00040325199961444014, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015887400002156937, "count": 8, "is_parallel": true, "self": 0.0015887400002156937 } } } } } } }, "UnityEnvironment.step": { "total": 1497.8651134759973, "count": 64202, "is_parallel": true, "self": 35.78623093093188, "children": { "UnityEnvironment._generate_step_input": { "total": 23.708459393006706, "count": 64202, "is_parallel": true, "self": 23.708459393006706 }, "communicator.exchange": { "total": 1327.306213158031, "count": 64202, "is_parallel": true, "self": 1327.306213158031 }, "steps_from_proto": { "total": 111.0642099940278, "count": 64202, "is_parallel": true, "self": 22.16578573504171, "children": { "_process_rank_one_or_two_observation": { "total": 88.8984242589861, "count": 513616, "is_parallel": true, "self": 88.8984242589861 } } } } } } } } } } }, "trainer_advance": { "total": 690.1682255410235, "count": 64203, "self": 2.965053096094607, "children": { "process_trajectory": { "total": 117.5684420469297, "count": 64203, "self": 117.28993616593016, "children": { "RLTrainer._checkpoint": { "total": 0.2785058809995462, "count": 2, "self": 0.2785058809995462 } } }, "_update_policy": { "total": 569.6347303979992, "count": 450, "self": 367.41860711900154, "children": { "TorchPPOOptimizer.update": { "total": 202.21612327899766, "count": 22869, "self": 202.21612327899766 } } } } } } }, "trainer_threads": { "total": 9.259997568733525e-07, "count": 1, "self": 9.259997568733525e-07 }, "TrainerController._save_models": { "total": 0.09854952800014871, "count": 1, "self": 0.0015566450001642806, "children": { "RLTrainer._checkpoint": { "total": 0.09699288299998443, "count": 1, "self": 0.09699288299998443 } } } } } } }