{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31607934832572937, "min": 0.2941468060016632, "max": 1.4997575283050537, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9411.5791015625, "min": 8753.80859375, "max": 45496.64453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989929.0, "min": 29937.0, "max": 989929.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989929.0, "min": 29937.0, "max": 989929.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5491355061531067, "min": -0.12188760936260223, "max": 0.5592450499534607, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 156.5036163330078, "min": -29.374914169311523, "max": 158.266357421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.040128033608198166, "min": 0.004869065713137388, "max": 0.29488691687583923, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.43648910522461, "min": 1.3243858814239502, "max": 71.0677490234375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0681892198176467, "min": 0.06461794108812076, "max": 0.07526596399100513, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9546490774470537, "min": 0.602127711928041, "max": 1.0837598194290574, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018610658634792172, "min": 0.0015262370220760248, "max": 0.018610658634792172, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2605492208870904, "min": 0.019841081286988322, "max": 0.26547901903298526, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.548633198107141e-06, "min": 7.548633198107141e-06, "max": 0.0002948416892194375, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010568086477349997, "min": 0.00010568086477349997, "max": 0.0036330712889762994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251617857142858, "min": 0.10251617857142858, "max": 0.19828056250000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352265000000002, "min": 1.4352265000000002, "max": 2.6110237, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002613662392857142, "min": 0.0002613662392857142, "max": 0.00982822819375, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036591273499999985, "min": 0.0036591273499999985, "max": 0.12112126763, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01659022830426693, "min": 0.015928657725453377, "max": 0.3901761770248413, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23226319253444672, "min": 0.22300121188163757, "max": 3.1214094161987305, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 339.7916666666667, "min": 327.9438202247191, "max": 985.1212121212121, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32620.0, "min": 16480.0, "max": 33180.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.576839567705368, "min": -0.8648000499515822, "max": 1.6495820017678013, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 151.37659849971533, "min": -28.538401648402214, "max": 151.37659849971533, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.576839567705368, "min": -0.8648000499515822, "max": 1.6495820017678013, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 151.37659849971533, "min": -28.538401648402214, "max": 151.37659849971533, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0582369302284557, "min": 0.0582369302284557, "max": 8.05782295325223, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.590745301931747, "min": 4.703726003062911, "max": 136.98299020528793, "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": "1678692171", "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 /content/ml-agents/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": "1.23.5", "end_time_seconds": "1678694687" }, "total": 2516.0087775250004, "count": 1, "self": 0.43676619300049424, "children": { "run_training.setup": { "total": 0.02706905500008361, "count": 1, "self": 0.02706905500008361 }, "TrainerController.start_learning": { "total": 2515.544942277, "count": 1, "self": 1.4642847758723292, "children": { "TrainerController._reset_env": { "total": 4.000240689999828, "count": 1, "self": 4.000240689999828 }, "TrainerController.advance": { "total": 2509.9938703021285, "count": 63841, "self": 1.5666010449813257, "children": { "env_step": { "total": 1717.9295965940596, "count": 63841, "self": 1591.5165658279652, "children": { "SubprocessEnvManager._take_step": { "total": 125.48052336902265, "count": 63841, "self": 5.14983035886371, "children": { "TorchPolicy.evaluate": { "total": 120.33069301015894, "count": 62548, "self": 40.9380188681248, "children": { "TorchPolicy.sample_actions": { "total": 79.39267414203414, "count": 62548, "self": 79.39267414203414 } } } } }, "workers": { "total": 0.9325073970717312, "count": 63841, "self": 0.0, "children": { "worker_root": { "total": 2510.159978522016, "count": 63841, "is_parallel": true, "self": 1044.620848939965, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001824300999942352, "count": 1, "is_parallel": true, "self": 0.0006854870002825919, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011388139996597602, "count": 8, "is_parallel": true, "self": 0.0011388139996597602 } } }, "UnityEnvironment.step": { "total": 0.047962387000097806, "count": 1, "is_parallel": true, "self": 0.000533984999947279, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005586470001617272, "count": 1, "is_parallel": true, "self": 0.0005586470001617272 }, "communicator.exchange": { "total": 0.04532294599994202, "count": 1, "is_parallel": true, "self": 0.04532294599994202 }, "steps_from_proto": { "total": 0.0015468090000467782, "count": 1, "is_parallel": true, "self": 0.0004470440003387921, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010997649997079861, "count": 8, "is_parallel": true, "self": 0.0010997649997079861 } } } } } } }, "UnityEnvironment.step": { "total": 1465.539129582051, "count": 63840, "is_parallel": true, "self": 32.45189212805053, "children": { "UnityEnvironment._generate_step_input": { "total": 23.668705895996936, "count": 63840, "is_parallel": true, "self": 23.668705895996936 }, "communicator.exchange": { "total": 1316.1493291881334, "count": 63840, "is_parallel": true, "self": 1316.1493291881334 }, "steps_from_proto": { "total": 93.26920236987007, "count": 63840, "is_parallel": true, "self": 23.173442589553815, "children": { "_process_rank_one_or_two_observation": { "total": 70.09575978031626, "count": 510720, "is_parallel": true, "self": 70.09575978031626 } } } } } } } } } } }, "trainer_advance": { "total": 790.4976726630875, "count": 63841, "self": 2.818897740061857, "children": { "process_trajectory": { "total": 181.58710566202762, "count": 63841, "self": 181.39038915802803, "children": { "RLTrainer._checkpoint": { "total": 0.19671650399959617, "count": 2, "self": 0.19671650399959617 } } }, "_update_policy": { "total": 606.0916692609981, "count": 459, "self": 208.238130523986, "children": { "TorchPPOOptimizer.update": { "total": 397.85353873701206, "count": 22836, "self": 397.85353873701206 } } } } } } }, "trainer_threads": { "total": 9.449995559407398e-07, "count": 1, "self": 9.449995559407398e-07 }, "TrainerController._save_models": { "total": 0.08654556399960711, "count": 1, "self": 0.0014732049994563567, "children": { "RLTrainer._checkpoint": { "total": 0.08507235900015075, "count": 1, "self": 0.08507235900015075 } } } } } } }