{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42387664318084717, "min": 0.4210941791534424, "max": 1.5118767023086548, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12777.337890625, "min": 12592.400390625, "max": 45864.29296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989975.0, "min": 29970.0, "max": 989975.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989975.0, "min": 29970.0, "max": 989975.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6737097501754761, "min": -0.10080820322036743, "max": 0.6737097501754761, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 195.37582397460938, "min": -24.294776916503906, "max": 195.37582397460938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020910434424877167, "min": -0.0059075928293168545, "max": 0.2043485939502716, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.06402587890625, "min": -1.6423108577728271, "max": 48.63496398925781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0728138422938155, "min": 0.06492625615657022, "max": 0.07584396281212122, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.019393792113417, "min": 0.5065314814262024, "max": 1.0766771016351413, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016866612575805736, "min": 0.0007491410013859851, "max": 0.018607803237890557, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23613257606128032, "min": 0.010487974019403792, "max": 0.2605092453304678, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.428311809642857e-06, "min": 7.428311809642857e-06, "max": 0.00029523763015888574, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000103996365335, "min": 0.000103996365335, "max": 0.003508752830415799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247607142857143, "min": 0.10247607142857143, "max": 0.19841254285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434665, "min": 1.3888878, "max": 2.569584200000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025735953571428573, "min": 0.00025735953571428573, "max": 0.009841413031428572, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036030335000000004, "min": 0.0036030335000000004, "max": 0.11698146158, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010285760276019573, "min": 0.010285760276019573, "max": 0.32646656036376953, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14400064945220947, "min": 0.14400064945220947, "max": 2.2852659225463867, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 282.302752293578, "min": 282.302752293578, "max": 994.8214285714286, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30771.0, "min": 16513.0, "max": 32673.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7172962773453306, "min": -0.9294303529190294, "max": 1.7172962773453306, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 185.4679979532957, "min": -30.671201646327972, "max": 185.4679979532957, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7172962773453306, "min": -0.9294303529190294, "max": 1.7172962773453306, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 185.4679979532957, "min": -30.671201646327972, "max": 185.4679979532957, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030009685024938167, "min": 0.030009685024938167, "max": 5.894349992713508, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.241045982693322, "min": 3.2328968545189127, "max": 100.20394987612963, "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": "1696075331", "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": "1696077707" }, "total": 2375.461250674, "count": 1, "self": 0.5283805410003879, "children": { "run_training.setup": { "total": 0.06337126699986584, "count": 1, "self": 0.06337126699986584 }, "TrainerController.start_learning": { "total": 2374.869498866, "count": 1, "self": 1.6667999599326322, "children": { "TrainerController._reset_env": { "total": 4.214924462000226, "count": 1, "self": 4.214924462000226 }, "TrainerController.advance": { "total": 2368.8929559560665, "count": 64031, "self": 1.6138708701055293, "children": { "env_step": { "total": 1696.943633516953, "count": 64031, "self": 1573.9700771099724, "children": { "SubprocessEnvManager._take_step": { "total": 121.9837056270319, "count": 64031, "self": 5.209705626010418, "children": { "TorchPolicy.evaluate": { "total": 116.77400000102148, "count": 62554, "self": 116.77400000102148 } } }, "workers": { "total": 0.9898507799487106, "count": 64031, "self": 0.0, "children": { "worker_root": { "total": 2368.9369219600203, "count": 64031, "is_parallel": true, "self": 922.4427267720118, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018291300000328192, "count": 1, "is_parallel": true, "self": 0.0006048739999187092, "children": { "_process_rank_one_or_two_observation": { "total": 0.00122425600011411, "count": 8, "is_parallel": true, "self": 0.00122425600011411 } } }, "UnityEnvironment.step": { "total": 0.04885685700014619, "count": 1, "is_parallel": true, "self": 0.0005806250003388413, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048122299995156936, "count": 1, "is_parallel": true, "self": 0.00048122299995156936 }, "communicator.exchange": { "total": 0.04497982099996989, "count": 1, "is_parallel": true, "self": 0.04497982099996989 }, "steps_from_proto": { "total": 0.002815187999885893, "count": 1, "is_parallel": true, "self": 0.0004092160002073797, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024059719996785134, "count": 8, "is_parallel": true, "self": 0.0024059719996785134 } } } } } } }, "UnityEnvironment.step": { "total": 1446.4941951880085, "count": 64030, "is_parallel": true, "self": 36.56855791503585, "children": { "UnityEnvironment._generate_step_input": { "total": 25.064149035975106, "count": 64030, "is_parallel": true, "self": 25.064149035975106 }, "communicator.exchange": { "total": 1269.4150293650025, "count": 64030, "is_parallel": true, "self": 1269.4150293650025 }, "steps_from_proto": { "total": 115.44645887199499, "count": 64030, "is_parallel": true, "self": 23.36288908590973, "children": { "_process_rank_one_or_two_observation": { "total": 92.08356978608526, "count": 512240, "is_parallel": true, "self": 92.08356978608526 } } } } } } } } } } }, "trainer_advance": { "total": 670.335451569008, "count": 64031, "self": 3.0303913119112167, "children": { "process_trajectory": { "total": 120.30018678510123, "count": 64031, "self": 120.08617473110144, "children": { "RLTrainer._checkpoint": { "total": 0.21401205399979517, "count": 2, "self": 0.21401205399979517 } } }, "_update_policy": { "total": 547.0048734719956, "count": 456, "self": 356.1343766669497, "children": { "TorchPPOOptimizer.update": { "total": 190.87049680504583, "count": 22800, "self": 190.87049680504583 } } } } } } }, "trainer_threads": { "total": 1.0540002222114708e-06, "count": 1, "self": 1.0540002222114708e-06 }, "TrainerController._save_models": { "total": 0.094817434000106, "count": 1, "self": 0.0014258139999583364, "children": { "RLTrainer._checkpoint": { "total": 0.09339162000014767, "count": 1, "self": 0.09339162000014767 } } } } } } }