{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47176626324653625, "min": 0.46518227458000183, "max": 1.3777782917022705, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14160.5361328125, "min": 13888.482421875, "max": 41796.28125, "count": 33 }, "Pyramids.Step.mean": { "value": 989895.0, "min": 29917.0, "max": 989895.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989895.0, "min": 29917.0, "max": 989895.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43828558921813965, "min": -0.08837016671895981, "max": 0.43828558921813965, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 116.14568328857422, "min": -21.297210693359375, "max": 116.14568328857422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03551291674375534, "min": -0.0023928359150886536, "max": 0.4843681752681732, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.41092300415039, "min": -0.591030478477478, "max": 114.79525756835938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06766680878423531, "min": 0.06530937767516079, "max": 0.07411704861303968, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9473353229792943, "min": 0.5706476349850862, "max": 1.0880978634385805, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01645676122972786, "min": 0.0008676704845300252, "max": 0.01645676122972786, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23039465721619004, "min": 0.011279716298890328, "max": 0.23039465721619004, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.334818983664287e-06, "min": 7.334818983664287e-06, "max": 0.00029499885166704996, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010268746577130002, "min": 0.00010268746577130002, "max": 0.0036332932889022998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244490714285716, "min": 0.10244490714285716, "max": 0.19833295, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342287000000002, "min": 1.4342287000000002, "max": 2.6110977000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002542462235714286, "min": 0.0002542462235714286, "max": 0.009833461705, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035594471300000002, "min": 0.0035594471300000002, "max": 0.12112866023000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009727247059345245, "min": 0.009294754825532436, "max": 0.4815974533557892, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13618145883083344, "min": 0.13012656569480896, "max": 3.8527796268463135, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 403.64383561643837, "min": 403.64383561643837, "max": 989.5454545454545, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29466.0, "min": 16076.0, "max": 33059.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5087378180107556, "min": -0.9297030825506557, "max": 1.5087378180107556, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 111.6465985327959, "min": -30.68020172417164, "max": 111.6465985327959, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5087378180107556, "min": -0.9297030825506557, "max": 1.5087378180107556, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 111.6465985327959, "min": -30.68020172417164, "max": 111.6465985327959, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.041073933706266455, "min": 0.041073933706266455, "max": 9.814331170390634, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0394710942637175, "min": 2.7885703344945796, "max": 166.84362989664078, "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": "1747649704", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1747651927" }, "total": 2222.421426772, "count": 1, "self": 0.5355520149996664, "children": { "run_training.setup": { "total": 0.021206434000305308, "count": 1, "self": 0.021206434000305308 }, "TrainerController.start_learning": { "total": 2221.864668323, "count": 1, "self": 1.4421249210004135, "children": { "TrainerController._reset_env": { "total": 2.4179597070001364, "count": 1, "self": 2.4179597070001364 }, "TrainerController.advance": { "total": 2217.9131698039982, "count": 63516, "self": 1.4982360010130833, "children": { "env_step": { "total": 1527.0986634590322, "count": 63516, "self": 1370.000702677995, "children": { "SubprocessEnvManager._take_step": { "total": 156.26049936301433, "count": 63516, "self": 4.774691831050859, "children": { "TorchPolicy.evaluate": { "total": 151.48580753196347, "count": 62568, "self": 151.48580753196347 } } }, "workers": { "total": 0.83746141802294, "count": 63516, "self": 0.0, "children": { "worker_root": { "total": 2216.750852568064, "count": 63516, "is_parallel": true, "self": 962.4540250319674, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002003921999857994, "count": 1, "is_parallel": true, "self": 0.0006511029996545403, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013528190002034535, "count": 8, "is_parallel": true, "self": 0.0013528190002034535 } } }, "UnityEnvironment.step": { "total": 0.047664293000252655, "count": 1, "is_parallel": true, "self": 0.0005420460001914762, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004956960001436528, "count": 1, "is_parallel": true, "self": 0.0004956960001436528 }, "communicator.exchange": { "total": 0.044893984999816894, "count": 1, "is_parallel": true, "self": 0.044893984999816894 }, "steps_from_proto": { "total": 0.0017325660001006327, "count": 1, "is_parallel": true, "self": 0.00037881700018260744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013537489999180252, "count": 8, "is_parallel": true, "self": 0.0013537489999180252 } } } } } } }, "UnityEnvironment.step": { "total": 1254.2968275360968, "count": 63515, "is_parallel": true, "self": 32.112403698935395, "children": { "UnityEnvironment._generate_step_input": { "total": 23.058834181128077, "count": 63515, "is_parallel": true, "self": 23.058834181128077 }, "communicator.exchange": { "total": 1103.0432213819868, "count": 63515, "is_parallel": true, "self": 1103.0432213819868 }, "steps_from_proto": { "total": 96.08236827404653, "count": 63515, "is_parallel": true, "self": 19.526647883204078, "children": { "_process_rank_one_or_two_observation": { "total": 76.55572039084245, "count": 508120, "is_parallel": true, "self": 76.55572039084245 } } } } } } } } } } }, "trainer_advance": { "total": 689.316270343953, "count": 63516, "self": 2.8064678149580686, "children": { "process_trajectory": { "total": 128.6226289079973, "count": 63516, "self": 128.4207275829972, "children": { "RLTrainer._checkpoint": { "total": 0.20190132500010805, "count": 2, "self": 0.20190132500010805 } } }, "_update_policy": { "total": 557.8871736209976, "count": 455, "self": 311.4362503139664, "children": { "TorchPPOOptimizer.update": { "total": 246.4509233070312, "count": 22809, "self": 246.4509233070312 } } } } } } }, "trainer_threads": { "total": 9.970008250093088e-07, "count": 1, "self": 9.970008250093088e-07 }, "TrainerController._save_models": { "total": 0.09141289400031383, "count": 1, "self": 0.001474376999794913, "children": { "RLTrainer._checkpoint": { "total": 0.08993851700051891, "count": 1, "self": 0.08993851700051891 } } } } } } }