{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.33215370774269104, "min": 0.32744649052619934, "max": 1.3892465829849243, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9932.724609375, "min": 9833.873046875, "max": 42144.18359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989953.0, "min": 29939.0, "max": 989953.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989953.0, "min": 29939.0, "max": 989953.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5937961339950562, "min": -0.11402159184217453, "max": 0.6218114495277405, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.48153686523438, "min": -27.593225479125977, "max": 180.7646942138672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.012516348622739315, "min": -0.012516348622739315, "max": 0.2709921598434448, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.4670286178588867, "min": -3.4670286178588867, "max": 64.22514343261719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06869396578350316, "min": 0.06459258985151314, "max": 0.07344745011081477, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9617155209690443, "min": 0.4829088080640623, "max": 1.073747740963168, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016333643093731916, "min": 0.000436349039498401, "max": 0.01675893164929348, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22867100331224682, "min": 0.005672537513479213, "max": 0.24195401150192244, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.352561834892862e-06, "min": 7.352561834892862e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010293586568850007, "min": 0.00010293586568850007, "max": 0.0036338635887122, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245082142857144, "min": 0.10245082142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343115000000002, "min": 1.3886848, "max": 2.6112878000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025483706071428587, "min": 0.00025483706071428587, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003567718850000002, "min": 0.003567718850000002, "max": 0.12114765121999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01031650323420763, "min": 0.01031650323420763, "max": 0.505388617515564, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14443103969097137, "min": 0.14443103969097137, "max": 3.537720203399658, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 318.67045454545456, "min": 311.1595744680851, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28043.0, "min": 16866.0, "max": 32555.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6589677935016567, "min": -0.9997933854659399, "max": 1.6675616807125984, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.33019803464413, "min": -29.993801563978195, "max": 163.84699787199497, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6589677935016567, "min": -0.9997933854659399, "max": 1.6675616807125984, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.33019803464413, "min": -29.993801563978195, "max": 163.84699787199497, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03371351445913342, "min": 0.03371351445913342, "max": 10.180521801990622, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.933075757944607, "min": 2.933075757944607, "max": 173.06887063384056, "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": "1767328587", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1767330780" }, "total": 2192.7339807959997, "count": 1, "self": 0.4831833419993927, "children": { "run_training.setup": { "total": 0.030265897999925073, "count": 1, "self": 0.030265897999925073 }, "TrainerController.start_learning": { "total": 2192.2205315560004, "count": 1, "self": 1.305473461992733, "children": { "TrainerController._reset_env": { "total": 2.8169025019997207, "count": 1, "self": 2.8169025019997207 }, "TrainerController.advance": { "total": 2188.021086805009, "count": 64008, "self": 1.344332832382861, "children": { "env_step": { "total": 1544.5402321089496, "count": 64008, "self": 1399.1370038446803, "children": { "SubprocessEnvManager._take_step": { "total": 144.5966223262658, "count": 64008, "self": 4.532296451163347, "children": { "TorchPolicy.evaluate": { "total": 140.06432587510244, "count": 62547, "self": 140.06432587510244 } } }, "workers": { "total": 0.8066059380034858, "count": 64008, "self": 0.0, "children": { "worker_root": { "total": 2185.762246034932, "count": 64008, "is_parallel": true, "self": 899.4077341828397, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025492999993730336, "count": 1, "is_parallel": true, "self": 0.00076713799717254, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017821620022004936, "count": 8, "is_parallel": true, "self": 0.0017821620022004936 } } }, "UnityEnvironment.step": { "total": 0.06180092899921874, "count": 1, "is_parallel": true, "self": 0.0015726219990028767, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004742460005218163, "count": 1, "is_parallel": true, "self": 0.0004742460005218163 }, "communicator.exchange": { "total": 0.057037986000068486, "count": 1, "is_parallel": true, "self": 0.057037986000068486 }, "steps_from_proto": { "total": 0.0027160749996255618, "count": 1, "is_parallel": true, "self": 0.00034630899972398765, "children": { "_process_rank_one_or_two_observation": { "total": 0.002369765999901574, "count": 8, "is_parallel": true, "self": 0.002369765999901574 } } } } } } }, "UnityEnvironment.step": { "total": 1286.3545118520924, "count": 64007, "is_parallel": true, "self": 32.66002140382807, "children": { "UnityEnvironment._generate_step_input": { "total": 22.41888816665596, "count": 64007, "is_parallel": true, "self": 22.41888816665596 }, "communicator.exchange": { "total": 1127.1192455026085, "count": 64007, "is_parallel": true, "self": 1127.1192455026085 }, "steps_from_proto": { "total": 104.1563567789999, "count": 64007, "is_parallel": true, "self": 22.140710835261416, "children": { "_process_rank_one_or_two_observation": { "total": 82.01564594373849, "count": 512056, "is_parallel": true, "self": 82.01564594373849 } } } } } } } } } } }, "trainer_advance": { "total": 642.1365218636765, "count": 64008, "self": 2.5777785456539277, "children": { "process_trajectory": { "total": 121.43874129000687, "count": 64008, "self": 121.24616865700591, "children": { "RLTrainer._checkpoint": { "total": 0.19257263300096383, "count": 2, "self": 0.19257263300096383 } } }, "_update_policy": { "total": 518.1200020280157, "count": 456, "self": 287.8494104679867, "children": { "TorchPPOOptimizer.update": { "total": 230.27059156002906, "count": 22842, "self": 230.27059156002906 } } } } } } }, "trainer_threads": { "total": 9.929990483215079e-07, "count": 1, "self": 9.929990483215079e-07 }, "TrainerController._save_models": { "total": 0.07706779399995867, "count": 1, "self": 0.0010116329995071283, "children": { "RLTrainer._checkpoint": { "total": 0.07605616100045154, "count": 1, "self": 0.07605616100045154 } } } } } } }