{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14200939238071442, "min": 0.13797780871391296, "max": 1.3743005990982056, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4198.93359375, "min": 4161.41064453125, "max": 41690.78125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999889.0, "min": 29985.0, "max": 2999889.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999889.0, "min": 29985.0, "max": 2999889.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6267638802528381, "min": -0.09637092053890228, "max": 0.8378081321716309, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.1206512451172, "min": -23.225391387939453, "max": 255.53147888183594, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.001505560940131545, "min": -0.06070947274565697, "max": 0.21783433854579926, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.42306262254714966, "min": -16.937942504882812, "max": 52.062408447265625, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07366944952047473, "min": 0.06392107111330714, "max": 0.07372342615937148, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0313722932866463, "min": 0.576497116336872, "max": 1.1012520589917103, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015957078649773308, "min": 0.00018244644150545246, "max": 0.01759593220014635, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2233991010968263, "min": 0.002371803739570882, "max": 0.24849804323942712, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4826852200904798e-06, "min": 1.4826852200904798e-06, "max": 0.00029825712558095835, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0757593081266716e-05, "min": 2.0757593081266716e-05, "max": 0.003937527187491, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049419523809525, "min": 0.10049419523809525, "max": 0.19941904166666669, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069187333333335, "min": 1.4069187333333335, "max": 2.812509, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9370104285714405e-05, "min": 5.9370104285714405e-05, "max": 0.0099419622625, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008311814600000017, "min": 0.0008311814600000017, "max": 0.1312696491, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005064699333161116, "min": 0.00493383314460516, "max": 0.3530867099761963, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07090578973293304, "min": 0.06983774155378342, "max": 2.8246936798095703, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 274.5740740740741, "min": 212.05109489051094, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29654.0, "min": 17295.0, "max": 34226.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6513296122904177, "min": -0.9999355356539449, "max": 1.788891296347846, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 178.3435981273651, "min": -31.99480164051056, "max": 246.86699889600277, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6513296122904177, "min": -0.9999355356539449, "max": 1.788891296347846, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 178.3435981273651, "min": -31.99480164051056, "max": 246.86699889600277, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014571904972129871, "min": 0.011917844449680717, "max": 6.574219990883851, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5737657369900262, "min": 1.4908536695147632, "max": 118.3359598359093, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676277815", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676285124" }, "total": 7309.126956757, "count": 1, "self": 0.8773278580001715, "children": { "run_training.setup": { "total": 0.10787730799984274, "count": 1, "self": 0.10787730799984274 }, "TrainerController.start_learning": { "total": 7308.141751591, "count": 1, "self": 4.150038159878022, "children": { "TrainerController._reset_env": { "total": 6.160198066000248, "count": 1, "self": 6.160198066000248 }, "TrainerController.advance": { "total": 7297.68711489612, "count": 194984, "self": 4.425999421555389, "children": { "env_step": { "total": 5146.5966936915665, "count": 194984, "self": 4815.018203268835, "children": { "SubprocessEnvManager._take_step": { "total": 329.0441827677023, "count": 194984, "self": 13.33605994587515, "children": { "TorchPolicy.evaluate": { "total": 315.70812282182715, "count": 187540, "self": 105.62295129113409, "children": { "TorchPolicy.sample_actions": { "total": 210.08517153069306, "count": 187540, "self": 210.08517153069306 } } } } }, "workers": { "total": 2.5343076550284422, "count": 194984, "self": 0.0, "children": { "worker_root": { "total": 7293.0554230338275, "count": 194984, "is_parallel": true, "self": 2816.8865753637456, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017056420001608785, "count": 1, "is_parallel": true, "self": 0.0006191340007717372, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010865079993891413, "count": 8, "is_parallel": true, "self": 0.0010865079993891413 } } }, "UnityEnvironment.step": { "total": 0.05033836999973573, "count": 1, "is_parallel": true, "self": 0.0005383039997468586, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005089450000923534, "count": 1, "is_parallel": true, "self": 0.0005089450000923534 }, "communicator.exchange": { "total": 0.04767202699986228, "count": 1, "is_parallel": true, "self": 0.04767202699986228 }, "steps_from_proto": { "total": 0.001619094000034238, "count": 1, "is_parallel": true, "self": 0.00041834099965853966, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012007530003756983, "count": 8, "is_parallel": true, "self": 0.0012007530003756983 } } } } } } }, "UnityEnvironment.step": { "total": 4476.168847670082, "count": 194983, "is_parallel": true, "self": 93.57602438924368, "children": { "UnityEnvironment._generate_step_input": { "total": 68.17197910049617, "count": 194983, "is_parallel": true, "self": 68.17197910049617 }, "communicator.exchange": { "total": 4012.7425107974354, "count": 194983, "is_parallel": true, "self": 4012.7425107974354 }, "steps_from_proto": { "total": 301.6783333829062, "count": 194983, "is_parallel": true, "self": 67.51753665777187, "children": { "_process_rank_one_or_two_observation": { "total": 234.16079672513433, "count": 1559864, "is_parallel": true, "self": 234.16079672513433 } } } } } } } } } } }, "trainer_advance": { "total": 2146.6644217829985, "count": 194984, "self": 8.22395171224207, "children": { "process_trajectory": { "total": 474.3837748597816, "count": 194984, "self": 473.7917498367824, "children": { "RLTrainer._checkpoint": { "total": 0.5920250229992234, "count": 6, "self": 0.5920250229992234 } } }, "_update_policy": { "total": 1664.0566952109748, "count": 1401, "self": 642.8292283861147, "children": { "TorchPPOOptimizer.update": { "total": 1021.2274668248601, "count": 68319, "self": 1021.2274668248601 } } } } } } }, "trainer_threads": { "total": 1.1890006135217845e-06, "count": 1, "self": 1.1890006135217845e-06 }, "TrainerController._save_models": { "total": 0.14439928000138025, "count": 1, "self": 0.0020599190011125756, "children": { "RLTrainer._checkpoint": { "total": 0.14233936100026767, "count": 1, "self": 0.14233936100026767 } } } } } } }