{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4244535565376282, "min": 0.42294439673423767, "max": 1.4268078804016113, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12801.51953125, "min": 12695.0986328125, "max": 43283.64453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29952.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29952.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6406899690628052, "min": -0.10473007708787918, "max": 0.6406899690628052, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.15939331054688, "min": -25.239948272705078, "max": 185.15939331054688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004117829725146294, "min": -0.004117829725146294, "max": 0.2629777193069458, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.1900527477264404, "min": -1.1900527477264404, "max": 63.64060974121094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06812349290475159, "min": 0.0635300489248599, "max": 0.07394954918615908, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9537289006665222, "min": 0.5119657118626785, "max": 1.1092432377923862, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01707030946382482, "min": 0.00045798211453801645, "max": 0.01707030946382482, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23898433249354747, "min": 0.005953767488994214, "max": 0.23898433249354747, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.461761798492859e-06, "min": 7.461761798492859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010446466517890002, "min": 0.00010446466517890002, "max": 0.0037585870471376994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248722142857145, "min": 0.10248722142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348211000000002, "min": 1.3886848, "max": 2.6528623, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002584734207142858, "min": 0.0002584734207142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003618627890000001, "min": 0.003618627890000001, "max": 0.12530094377, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008988547138869762, "min": 0.008988547138869762, "max": 0.46923691034317017, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12583966553211212, "min": 0.12583966553211212, "max": 3.284658432006836, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 274.6857142857143, "min": 274.6857142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28842.0, "min": 15984.0, "max": 33948.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7259523696842647, "min": -1.0000000521540642, "max": 1.7259523696842647, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 181.2249988168478, "min": -28.767001517117023, "max": 181.2249988168478, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7259523696842647, "min": -1.0000000521540642, "max": 1.7259523696842647, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 181.2249988168478, "min": -28.767001517117023, "max": 181.2249988168478, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02522160971005048, "min": 0.02522160971005048, "max": 9.687635842710733, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6482690195553005, "min": 2.6482690195553005, "max": 155.00217348337173, "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": "1733566941", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1733569149" }, "total": 2208.0239664769997, "count": 1, "self": 0.4898817559997042, "children": { "run_training.setup": { "total": 0.054378752000047825, "count": 1, "self": 0.054378752000047825 }, "TrainerController.start_learning": { "total": 2207.479705969, "count": 1, "self": 1.308461412977067, "children": { "TrainerController._reset_env": { "total": 2.258942081999976, "count": 1, "self": 2.258942081999976 }, "TrainerController.advance": { "total": 2203.823205378023, "count": 64159, "self": 1.375892323086191, "children": { "env_step": { "total": 1515.3065768289348, "count": 64159, "self": 1371.8963863879121, "children": { "SubprocessEnvManager._take_step": { "total": 142.62680482900646, "count": 64159, "self": 4.471776400049748, "children": { "TorchPolicy.evaluate": { "total": 138.1550284289567, "count": 62565, "self": 138.1550284289567 } } }, "workers": { "total": 0.7833856120162181, "count": 64159, "self": 0.0, "children": { "worker_root": { "total": 2202.6516069509753, "count": 64159, "is_parallel": true, "self": 944.7722812009272, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002068687000019054, "count": 1, "is_parallel": true, "self": 0.0006445750002512796, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014241119997677743, "count": 8, "is_parallel": true, "self": 0.0014241119997677743 } } }, "UnityEnvironment.step": { "total": 0.048407217999965724, "count": 1, "is_parallel": true, "self": 0.0006296639999163745, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005142730001352902, "count": 1, "is_parallel": true, "self": 0.0005142730001352902 }, "communicator.exchange": { "total": 0.04568080600006397, "count": 1, "is_parallel": true, "self": 0.04568080600006397 }, "steps_from_proto": { "total": 0.001582474999850092, "count": 1, "is_parallel": true, "self": 0.0003315469998597109, "children": { "_process_rank_one_or_two_observation": { "total": 0.001250927999990381, "count": 8, "is_parallel": true, "self": 0.001250927999990381 } } } } } } }, "UnityEnvironment.step": { "total": 1257.879325750048, "count": 64158, "is_parallel": true, "self": 32.200059572999635, "children": { "UnityEnvironment._generate_step_input": { "total": 22.5322458620019, "count": 64158, "is_parallel": true, "self": 22.5322458620019 }, "communicator.exchange": { "total": 1109.1566616949722, "count": 64158, "is_parallel": true, "self": 1109.1566616949722 }, "steps_from_proto": { "total": 93.9903586200744, "count": 64158, "is_parallel": true, "self": 18.44389080215774, "children": { "_process_rank_one_or_two_observation": { "total": 75.54646781791666, "count": 513264, "is_parallel": true, "self": 75.54646781791666 } } } } } } } } } } }, "trainer_advance": { "total": 687.1407362260022, "count": 64159, "self": 2.486621429931347, "children": { "process_trajectory": { "total": 133.81213751606788, "count": 64159, "self": 133.5776646530678, "children": { "RLTrainer._checkpoint": { "total": 0.23447286300006454, "count": 2, "self": 0.23447286300006454 } } }, "_update_policy": { "total": 550.841977280003, "count": 457, "self": 308.6473247049812, "children": { "TorchPPOOptimizer.update": { "total": 242.1946525750218, "count": 22794, "self": 242.1946525750218 } } } } } } }, "trainer_threads": { "total": 9.93999947240809e-07, "count": 1, "self": 9.93999947240809e-07 }, "TrainerController._save_models": { "total": 0.08909610199998497, "count": 1, "self": 0.002040319000116142, "children": { "RLTrainer._checkpoint": { "total": 0.08705578299986882, "count": 1, "self": 0.08705578299986882 } } } } } } }