{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3638289272785187, "min": 0.35986775159835815, "max": 1.4710935354232788, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10839.19140625, "min": 10801.7900390625, "max": 44627.09375, "count": 33 }, "Pyramids.Step.mean": { "value": 989920.0, "min": 29946.0, "max": 989920.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989920.0, "min": 29946.0, "max": 989920.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5525236129760742, "min": -0.09329217672348022, "max": 0.6201168298721313, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 152.49652099609375, "min": -22.483413696289062, "max": 176.73329162597656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06018223240971565, "min": -0.046109721064567566, "max": 0.24697653949260712, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 16.61029624938965, "min": -12.587953567504883, "max": 59.27436828613281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07092753760645995, "min": 0.0647525040213779, "max": 0.07287893897163564, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0639130640968992, "min": 0.5830315117730851, "max": 1.0802229808657156, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01667636141776004, "min": 0.0007201647848999739, "max": 0.01667636141776004, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2501454212664006, "min": 0.006481483064099765, "max": 0.2501454212664006, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.457157514313337e-06, "min": 7.457157514313337e-06, "max": 0.00029520682659772495, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011185736271470005, "min": 0.00011185736271470005, "max": 0.0032527823157393, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248568666666666, "min": 0.10248568666666666, "max": 0.19840227500000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372853, "min": 1.4774409, "max": 2.4432977, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002583200980000002, "min": 0.0002583200980000002, "max": 0.0098403872725, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038748014700000027, "min": 0.0038748014700000027, "max": 0.10844764393, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015570336952805519, "min": 0.015570336952805519, "max": 0.41925716400146484, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23355504870414734, "min": 0.2234107106924057, "max": 3.3540573120117188, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 327.60227272727275, "min": 306.8255813953488, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28829.0, "min": 15978.0, "max": 33158.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6041886152022264, "min": -0.999962551984936, "max": 1.6931744048068689, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 141.16859813779593, "min": -31.998801663517952, "max": 163.0695983991027, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6041886152022264, "min": -0.999962551984936, "max": 1.6931744048068689, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 141.16859813779593, "min": -31.998801663517952, "max": 163.0695983991027, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.053141101516799114, "min": 0.05008875402056092, "max": 8.086697021499276, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.676416933478322, "min": 4.307632845768239, "max": 129.38715234398842, "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": "1689198620", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689200718" }, "total": 2097.210568888, "count": 1, "self": 1.3859077720007917, "children": { "run_training.setup": { "total": 0.040927635999878476, "count": 1, "self": 0.040927635999878476 }, "TrainerController.start_learning": { "total": 2095.7837334799997, "count": 1, "self": 1.1790282529332217, "children": { "TrainerController._reset_env": { "total": 4.779942886000072, "count": 1, "self": 4.779942886000072 }, "TrainerController.advance": { "total": 2089.676150857066, "count": 63849, "self": 1.2671558850743168, "children": { "env_step": { "total": 1455.893603331953, "count": 63849, "self": 1352.02090620887, "children": { "SubprocessEnvManager._take_step": { "total": 103.14454754199483, "count": 63849, "self": 4.392326678938161, "children": { "TorchPolicy.evaluate": { "total": 98.75222086305666, "count": 62553, "self": 98.75222086305666 } } }, "workers": { "total": 0.7281495810882461, "count": 63849, "self": 0.0, "children": { "worker_root": { "total": 2091.1870691331005, "count": 63849, "is_parallel": true, "self": 844.2947302190441, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017951269999230135, "count": 1, "is_parallel": true, "self": 0.0005461620000914991, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012489649998315144, "count": 8, "is_parallel": true, "self": 0.0012489649998315144 } } }, "UnityEnvironment.step": { "total": 0.08881514299991977, "count": 1, "is_parallel": true, "self": 0.0005854040000485838, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004540400000223599, "count": 1, "is_parallel": true, "self": 0.0004540400000223599 }, "communicator.exchange": { "total": 0.08577735999983815, "count": 1, "is_parallel": true, "self": 0.08577735999983815 }, "steps_from_proto": { "total": 0.0019983390000106738, "count": 1, "is_parallel": true, "self": 0.00039775199979885656, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016005870002118172, "count": 8, "is_parallel": true, "self": 0.0016005870002118172 } } } } } } }, "UnityEnvironment.step": { "total": 1246.8923389140564, "count": 63848, "is_parallel": true, "self": 33.120213198983265, "children": { "UnityEnvironment._generate_step_input": { "total": 21.984421469950803, "count": 63848, "is_parallel": true, "self": 21.984421469950803 }, "communicator.exchange": { "total": 1091.8101594150708, "count": 63848, "is_parallel": true, "self": 1091.8101594150708 }, "steps_from_proto": { "total": 99.97754483005156, "count": 63848, "is_parallel": true, "self": 18.98872540714524, "children": { "_process_rank_one_or_two_observation": { "total": 80.98881942290632, "count": 510784, "is_parallel": true, "self": 80.98881942290632 } } } } } } } } } } }, "trainer_advance": { "total": 632.5153916400388, "count": 63849, "self": 2.3195505671103547, "children": { "process_trajectory": { "total": 104.53916845492836, "count": 63849, "self": 104.27983960692768, "children": { "RLTrainer._checkpoint": { "total": 0.2593288480006777, "count": 2, "self": 0.2593288480006777 } } }, "_update_policy": { "total": 525.6566726180001, "count": 447, "self": 338.59884949396474, "children": { "TorchPPOOptimizer.update": { "total": 187.0578231240354, "count": 22833, "self": 187.0578231240354 } } } } } } }, "trainer_threads": { "total": 1.1980000635958277e-06, "count": 1, "self": 1.1980000635958277e-06 }, "TrainerController._save_models": { "total": 0.14861028600034842, "count": 1, "self": 0.001858135000020411, "children": { "RLTrainer._checkpoint": { "total": 0.146752151000328, "count": 1, "self": 0.146752151000328 } } } } } } }