{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.12423394620418549, "min": 0.12296582013368607, "max": 1.4386978149414062, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3778.69970703125, "min": 3655.52783203125, "max": 43644.3359375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999983.0, "min": 29952.0, "max": 2999983.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999983.0, "min": 29952.0, "max": 2999983.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7895793914794922, "min": -0.10521090030670166, "max": 0.8525463938713074, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 231.3467559814453, "min": -25.35582733154297, "max": 260.0266418457031, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009593086317181587, "min": -0.025728631764650345, "max": 0.4012734293937683, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.810774326324463, "min": -7.521064758300781, "max": 96.70689392089844, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0654072828509102, "min": 0.06368785717880682, "max": 0.07439415260437056, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9157019599127428, "min": 0.5072668978058594, "max": 1.1033470515006532, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01435509639781057, "min": 0.00011339722269022704, "max": 0.01672223555506207, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20097134956934798, "min": 0.0014741638949729516, "max": 0.25083353332593106, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5312923467452387e-06, "min": 1.5312923467452387e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.143809285443334e-05, "min": 2.143809285443334e-05, "max": 0.003982422372525933, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051039761904763, "min": 0.10051039761904763, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071455666666668, "min": 1.3962282666666668, "max": 2.827474066666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.098872214285716e-05, "min": 6.098872214285716e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008538421100000003, "min": 0.0008538421100000003, "max": 0.13276465926, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007616333197802305, "min": 0.007522854488343, "max": 0.672101616859436, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1066286638379097, "min": 0.10531996190547943, "max": 4.704711437225342, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 225.0546875, "min": 213.08965517241379, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28807.0, "min": 15984.0, "max": 33311.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7575327922822908, "min": -1.0000000521540642, "max": 1.7864255218218403, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 224.96419741213322, "min": -29.958001665771008, "max": 257.1017983108759, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7575327922822908, "min": -1.0000000521540642, "max": 1.7864255218218403, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 224.96419741213322, "min": -29.958001665771008, "max": 257.1017983108759, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01798438865262142, "min": 0.01778946284060206, "max": 12.793168457224965, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3020017475355417, "min": 2.2497354806546355, "max": 204.69069531559944, "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": "1679322850", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679329982" }, "total": 7132.43992697, "count": 1, "self": 0.4756166420002046, "children": { "run_training.setup": { "total": 0.1006640570003583, "count": 1, "self": 0.1006640570003583 }, "TrainerController.start_learning": { "total": 7131.863646270999, "count": 1, "self": 4.1454138361859805, "children": { "TrainerController._reset_env": { "total": 5.672157027000139, "count": 1, "self": 5.672157027000139 }, "TrainerController.advance": { "total": 7121.946855036812, "count": 194919, "self": 4.546268633949694, "children": { "env_step": { "total": 5263.692359528293, "count": 194919, "self": 4935.506148401942, "children": { "SubprocessEnvManager._take_step": { "total": 325.53673449920825, "count": 194919, "self": 14.492430762919867, "children": { "TorchPolicy.evaluate": { "total": 311.0443037362884, "count": 187569, "self": 311.0443037362884 } } }, "workers": { "total": 2.6494766271434855, "count": 194919, "self": 0.0, "children": { "worker_root": { "total": 7116.639362089073, "count": 194919, "is_parallel": true, "self": 2543.752831216836, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018360630001552636, "count": 1, "is_parallel": true, "self": 0.0006017419982526917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012343210019025719, "count": 8, "is_parallel": true, "self": 0.0012343210019025719 } } }, "UnityEnvironment.step": { "total": 0.047013114000037604, "count": 1, "is_parallel": true, "self": 0.0005331450001904159, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004956100001436425, "count": 1, "is_parallel": true, "self": 0.0004956100001436425 }, "communicator.exchange": { "total": 0.04426400499960437, "count": 1, "is_parallel": true, "self": 0.04426400499960437 }, "steps_from_proto": { "total": 0.001720354000099178, "count": 1, "is_parallel": true, "self": 0.0003948240000681835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013255300000309944, "count": 8, "is_parallel": true, "self": 0.0013255300000309944 } } } } } } }, "UnityEnvironment.step": { "total": 4572.886530872237, "count": 194918, "is_parallel": true, "self": 94.76476257547074, "children": { "UnityEnvironment._generate_step_input": { "total": 72.09547024768926, "count": 194918, "is_parallel": true, "self": 72.09547024768926 }, "communicator.exchange": { "total": 4118.611200276771, "count": 194918, "is_parallel": true, "self": 4118.611200276771 }, "steps_from_proto": { "total": 287.41509777230567, "count": 194918, "is_parallel": true, "self": 62.00402547361409, "children": { "_process_rank_one_or_two_observation": { "total": 225.41107229869158, "count": 1559344, "is_parallel": true, "self": 225.41107229869158 } } } } } } } } } } }, "trainer_advance": { "total": 1853.708226874569, "count": 194919, "self": 8.018446898497132, "children": { "process_trajectory": { "total": 375.8056128270673, "count": 194919, "self": 375.1678883580653, "children": { "RLTrainer._checkpoint": { "total": 0.6377244690020234, "count": 6, "self": 0.6377244690020234 } } }, "_update_policy": { "total": 1469.8841671490045, "count": 1398, "self": 938.1967370970115, "children": { "TorchPPOOptimizer.update": { "total": 531.687430051993, "count": 68346, "self": 531.687430051993 } } } } } } }, "trainer_threads": { "total": 8.280003385152668e-07, "count": 1, "self": 8.280003385152668e-07 }, "TrainerController._save_models": { "total": 0.0992195430007996, "count": 1, "self": 0.0013916990010329755, "children": { "RLTrainer._checkpoint": { "total": 0.09782784399976663, "count": 1, "self": 0.09782784399976663 } } } } } } }