{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36228060722351074, "min": 0.36228060722351074, "max": 1.4557124376296997, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10804.6572265625, "min": 10804.6572265625, "max": 44160.4921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5167350769042969, "min": -0.1052287369966507, "max": 0.5189744234085083, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.10214233398438, "min": -25.57058334350586, "max": 143.75592041015625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.08412662148475647, "min": 0.05415404587984085, "max": 0.5788809657096863, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 23.13482093811035, "min": 13.406205177307129, "max": 137.19479370117188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06876432506007395, "min": 0.06614247815012057, "max": 0.07280106319588944, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9627005508410352, "min": 0.5094768675009891, "max": 1.0873266214832398, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016114696219336193, "min": 0.0005501797296438871, "max": 0.01657653617827843, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2256057470707067, "min": 0.007702516215014419, "max": 0.24864804267417642, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.699833147707139e-06, "min": 7.699833147707139e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010779766406789995, "min": 0.00010779766406789995, "max": 0.0036333517888827997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256657857142859, "min": 0.10256657857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359321000000003, "min": 1.3886848, "max": 2.6111171999999994, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002664011992857142, "min": 0.0002664011992857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037296167899999993, "min": 0.0037296167899999993, "max": 0.12113060828, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.05612374469637871, "min": 0.05028453469276428, "max": 0.7290673851966858, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.7857324481010437, "min": 0.7039834856987, "max": 5.103471755981445, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 355.20238095238096, "min": 355.20238095238096, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29837.0, "min": 15984.0, "max": 32773.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5495309367598522, "min": -1.0000000521540642, "max": 1.5879950393681173, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.1605986878276, "min": -28.7896016985178, "max": 130.1605986878276, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5495309367598522, "min": -1.0000000521540642, "max": 1.5879950393681173, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.1605986878276, "min": -28.7896016985178, "max": 130.1605986878276, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.20080880816732088, "min": 0.19038125768449032, "max": 14.540362916886806, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 16.867939886054955, "min": 15.192091762786731, "max": 232.6458066701889, "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": "1732080119", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732083438" }, "total": 3318.624005306, "count": 1, "self": 0.7569512729996859, "children": { "run_training.setup": { "total": 0.0943560409998554, "count": 1, "self": 0.0943560409998554 }, "TrainerController.start_learning": { "total": 3317.7726979920003, "count": 1, "self": 2.420487909998428, "children": { "TrainerController._reset_env": { "total": 3.3841081250000116, "count": 1, "self": 3.3841081250000116 }, "TrainerController.advance": { "total": 3311.888125975003, "count": 63707, "self": 2.6505303100880155, "children": { "env_step": { "total": 2167.3930541779605, "count": 63707, "self": 1995.6191026278173, "children": { "SubprocessEnvManager._take_step": { "total": 170.34121278605699, "count": 63707, "self": 7.464526736030166, "children": { "TorchPolicy.evaluate": { "total": 162.87668605002682, "count": 62566, "self": 162.87668605002682 } } }, "workers": { "total": 1.4327387640862526, "count": 63707, "self": 0.0, "children": { "worker_root": { "total": 3310.055319993981, "count": 63707, "is_parallel": true, "self": 1500.7472498200204, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005760346999977628, "count": 1, "is_parallel": true, "self": 0.0014778070003558241, "children": { "_process_rank_one_or_two_observation": { "total": 0.004282539999621804, "count": 8, "is_parallel": true, "self": 0.004282539999621804 } } }, "UnityEnvironment.step": { "total": 0.14743523299989647, "count": 1, "is_parallel": true, "self": 0.0007358359998761443, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006346790000861802, "count": 1, "is_parallel": true, "self": 0.0006346790000861802 }, "communicator.exchange": { "total": 0.1441741749999892, "count": 1, "is_parallel": true, "self": 0.1441741749999892 }, "steps_from_proto": { "total": 0.0018905429999449552, "count": 1, "is_parallel": true, "self": 0.0003900879992215778, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015004550007233775, "count": 8, "is_parallel": true, "self": 0.0015004550007233775 } } } } } } }, "UnityEnvironment.step": { "total": 1809.3080701739605, "count": 63706, "is_parallel": true, "self": 50.96299453086135, "children": { "UnityEnvironment._generate_step_input": { "total": 31.657531011012452, "count": 63706, "is_parallel": true, "self": 31.657531011012452 }, "communicator.exchange": { "total": 1594.1471244059978, "count": 63706, "is_parallel": true, "self": 1594.1471244059978 }, "steps_from_proto": { "total": 132.54042022608883, "count": 63706, "is_parallel": true, "self": 29.038801354029147, "children": { "_process_rank_one_or_two_observation": { "total": 103.50161887205968, "count": 509648, "is_parallel": true, "self": 103.50161887205968 } } } } } } } } } } }, "trainer_advance": { "total": 1141.8445414869543, "count": 63707, "self": 4.699436843959802, "children": { "process_trajectory": { "total": 173.32435570399502, "count": 63707, "self": 173.08021554599463, "children": { "RLTrainer._checkpoint": { "total": 0.24414015800039124, "count": 2, "self": 0.24414015800039124 } } }, "_update_policy": { "total": 963.8207489389995, "count": 455, "self": 386.2453780660071, "children": { "TorchPPOOptimizer.update": { "total": 577.5753708729924, "count": 22749, "self": 577.5753708729924 } } } } } } }, "trainer_threads": { "total": 1.4669994925498031e-06, "count": 1, "self": 1.4669994925498031e-06 }, "TrainerController._save_models": { "total": 0.07997451499977615, "count": 1, "self": 0.0017509089993836824, "children": { "RLTrainer._checkpoint": { "total": 0.07822360600039246, "count": 1, "self": 0.07822360600039246 } } } } } } }