{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35729846358299255, "min": 0.35568785667419434, "max": 1.3679313659667969, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10781.8388671875, "min": 10602.34375, "max": 41497.56640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3361831605434418, "min": -0.1151665672659874, "max": 0.4182727336883545, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 87.07144165039062, "min": -27.755142211914062, "max": 113.35191345214844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07570448517799377, "min": 0.0004983206745237112, "max": 0.3900524973869324, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 19.60746192932129, "min": 0.12757009267807007, "max": 92.44244384765625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06758757927759905, "min": 0.0641204020082957, "max": 0.07299535239528646, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9462261098863868, "min": 0.5103341364030775, "max": 1.0832388601362861, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012775110295998664, "min": 0.001285500948150886, "max": 0.01648509034033244, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1788515441439813, "min": 0.017997013274112402, "max": 0.2472763551049866, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.314676133235717e-06, "min": 7.314676133235717e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010240546586530004, "min": 0.00010240546586530004, "max": 0.0036337150887616994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243819285714285, "min": 0.10243819285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341347, "min": 1.3886848, "max": 2.6112383000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002535754664285715, "min": 0.0002535754664285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035500565300000016, "min": 0.0035500565300000016, "max": 0.12114270616999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015247063711285591, "min": 0.015213284641504288, "max": 0.5134950280189514, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21345889568328857, "min": 0.21345889568328857, "max": 3.5944650173187256, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 525.859649122807, "min": 418.59420289855075, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29974.0, "min": 15984.0, "max": 33315.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2635578723591672, "min": -1.0000000521540642, "max": 1.4654115720287613, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 72.02279872447252, "min": -29.3456017524004, "max": 103.68079825490713, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2635578723591672, "min": -1.0000000521540642, "max": 1.4654115720287613, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 72.02279872447252, "min": -29.3456017524004, "max": 103.68079825490713, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08268000463022761, "min": 0.06599868293082893, "max": 9.396346041932702, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.7127602639229735, "min": 4.553909122227196, "max": 150.34153667092323, "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": "1704706590", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704708213" }, "total": 1623.500536087, "count": 1, "self": 0.2204885959999956, "children": { "run_training.setup": { "total": 0.02965514000004532, "count": 1, "self": 0.02965514000004532 }, "TrainerController.start_learning": { "total": 1623.2503923509998, "count": 1, "self": 1.0889636469892139, "children": { "TrainerController._reset_env": { "total": 1.5400899649999928, "count": 1, "self": 1.5400899649999928 }, "TrainerController.advance": { "total": 1620.5466793130108, "count": 63641, "self": 1.1858897750216784, "children": { "env_step": { "total": 1006.9792002669788, "count": 63641, "self": 817.6621327908961, "children": { "SubprocessEnvManager._take_step": { "total": 188.57230744307049, "count": 63641, "self": 3.773091888079307, "children": { "TorchPolicy.evaluate": { "total": 184.79921555499118, "count": 62563, "self": 184.79921555499118 } } }, "workers": { "total": 0.7447600330121986, "count": 63641, "self": 0.0, "children": { "worker_root": { "total": 1620.6793645950097, "count": 63641, "is_parallel": true, "self": 876.556221574023, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013030730000309632, "count": 1, "is_parallel": true, "self": 0.0006111969998983113, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006918760001326518, "count": 8, "is_parallel": true, "self": 0.0006918760001326518 } } }, "UnityEnvironment.step": { "total": 0.025766861999954926, "count": 1, "is_parallel": true, "self": 0.00018732799992449145, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001561819999551517, "count": 1, "is_parallel": true, "self": 0.0001561819999551517 }, "communicator.exchange": { "total": 0.0249353690001044, "count": 1, "is_parallel": true, "self": 0.0249353690001044 }, "steps_from_proto": { "total": 0.0004879829999708818, "count": 1, "is_parallel": true, "self": 0.0001237000001310662, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003642829998398156, "count": 8, "is_parallel": true, "self": 0.0003642829998398156 } } } } } } }, "UnityEnvironment.step": { "total": 744.1231430209867, "count": 63640, "is_parallel": true, "self": 12.502218498024263, "children": { "UnityEnvironment._generate_step_input": { "total": 8.514299696994044, "count": 63640, "is_parallel": true, "self": 8.514299696994044 }, "communicator.exchange": { "total": 690.6087772519685, "count": 63640, "is_parallel": true, "self": 690.6087772519685 }, "steps_from_proto": { "total": 32.497847573999934, "count": 63640, "is_parallel": true, "self": 7.993378597930473, "children": { "_process_rank_one_or_two_observation": { "total": 24.50446897606946, "count": 509120, "is_parallel": true, "self": 24.50446897606946 } } } } } } } } } } }, "trainer_advance": { "total": 612.3815892710104, "count": 63641, "self": 2.155263177999359, "children": { "process_trajectory": { "total": 103.7041467080096, "count": 63641, "self": 103.55745747300944, "children": { "RLTrainer._checkpoint": { "total": 0.14668923500016717, "count": 2, "self": 0.14668923500016717 } } }, "_update_policy": { "total": 506.52217938500144, "count": 456, "self": 229.38016495398665, "children": { "TorchPPOOptimizer.update": { "total": 277.1420144310148, "count": 22794, "self": 277.1420144310148 } } } } } } }, "trainer_threads": { "total": 5.629999577649869e-07, "count": 1, "self": 5.629999577649869e-07 }, "TrainerController._save_models": { "total": 0.07465886299996782, "count": 1, "self": 0.0009840689999691676, "children": { "RLTrainer._checkpoint": { "total": 0.07367479399999866, "count": 1, "self": 0.07367479399999866 } } } } } } }