{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28850871324539185, "min": 0.28850871324539185, "max": 1.481791377067566, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8567.5546875, "min": 8567.5546875, "max": 44951.625, "count": 33 }, "Pyramids.Step.mean": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5664639472961426, "min": -0.09751632064580917, "max": 0.631919801235199, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 155.21112060546875, "min": -23.598949432373047, "max": 183.88865661621094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01418967917561531, "min": -0.0036025254521518946, "max": 0.26148971915245056, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.887972116470337, "min": -0.9510667324066162, "max": 62.75753402709961, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06711690029450915, "min": 0.06351086551772564, "max": 0.07293790684796754, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.939636604123128, "min": 0.47759051730484314, "max": 1.0276374082479345, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01679909037747642, "min": 0.0004550705946399824, "max": 0.016912353860159896, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2351872652846699, "min": 0.003185494162479877, "max": 0.23677295404223853, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.66640458742143e-06, "min": 7.66640458742143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010732966422390002, "min": 0.00010732966422390002, "max": 0.0032582546139151994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255543571428574, "min": 0.10255543571428574, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357761000000004, "min": 1.327104, "max": 2.4821624, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000265288027857143, "min": 0.000265288027857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003714032390000002, "min": 0.003714032390000002, "max": 0.10862987152000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014071226119995117, "min": 0.014071226119995117, "max": 0.46310392022132874, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19699716567993164, "min": 0.19699716567993164, "max": 3.241727352142334, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 352.32530120481925, "min": 294.19, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29243.0, "min": 15984.0, "max": 33789.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6235662511134723, "min": -1.0000000521540642, "max": 1.7065959423780441, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.7559988424182, "min": -32.000001668930054, "max": 168.95299829542637, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6235662511134723, "min": -1.0000000521540642, "max": 1.7065959423780441, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.7559988424182, "min": -32.000001668930054, "max": 168.95299829542637, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05152049591780236, "min": 0.04686120382775882, "max": 8.98849476967007, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.276201161177596, "min": 4.276201161177596, "max": 143.8159163147211, "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": "1723518303", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723520901" }, "total": 2598.839057718, "count": 1, "self": 0.694141536999723, "children": { "run_training.setup": { "total": 0.09467989399990984, "count": 1, "self": 0.09467989399990984 }, "TrainerController.start_learning": { "total": 2598.050236287, "count": 1, "self": 1.8244219039866039, "children": { "TrainerController._reset_env": { "total": 3.4984390169997823, "count": 1, "self": 3.4984390169997823 }, "TrainerController.advance": { "total": 2592.630405206014, "count": 63859, "self": 1.9964963559882563, "children": { "env_step": { "total": 1854.2718894229915, "count": 63859, "self": 1690.0204778139505, "children": { "SubprocessEnvManager._take_step": { "total": 163.11515019503804, "count": 63859, "self": 5.7586925060090834, "children": { "TorchPolicy.evaluate": { "total": 157.35645768902896, "count": 62551, "self": 157.35645768902896 } } }, "workers": { "total": 1.1362614140030018, "count": 63859, "self": 0.0, "children": { "worker_root": { "total": 2591.892845802115, "count": 63859, "is_parallel": true, "self": 1053.8497279190533, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031065100001796964, "count": 1, "is_parallel": true, "self": 0.0008254950007540174, "children": { "_process_rank_one_or_two_observation": { "total": 0.002281014999425679, "count": 8, "is_parallel": true, "self": 0.002281014999425679 } } }, "UnityEnvironment.step": { "total": 0.052211807999810844, "count": 1, "is_parallel": true, "self": 0.0006785059999856458, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005047999998168962, "count": 1, "is_parallel": true, "self": 0.0005047999998168962 }, "communicator.exchange": { "total": 0.049128727999686816, "count": 1, "is_parallel": true, "self": 0.049128727999686816 }, "steps_from_proto": { "total": 0.0018997740003214858, "count": 1, "is_parallel": true, "self": 0.00039312900025834097, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015066450000631448, "count": 8, "is_parallel": true, "self": 0.0015066450000631448 } } } } } } }, "UnityEnvironment.step": { "total": 1538.0431178830618, "count": 63858, "is_parallel": true, "self": 41.35288127308104, "children": { "UnityEnvironment._generate_step_input": { "total": 26.412912180875537, "count": 63858, "is_parallel": true, "self": 26.412912180875537 }, "communicator.exchange": { "total": 1354.065577954002, "count": 63858, "is_parallel": true, "self": 1354.065577954002 }, "steps_from_proto": { "total": 116.21174647510315, "count": 63858, "is_parallel": true, "self": 24.681452273079685, "children": { "_process_rank_one_or_two_observation": { "total": 91.53029420202347, "count": 510864, "is_parallel": true, "self": 91.53029420202347 } } } } } } } } } } }, "trainer_advance": { "total": 736.3620194270343, "count": 63859, "self": 3.4757341020690546, "children": { "process_trajectory": { "total": 144.85352401197406, "count": 63859, "self": 144.63813858797357, "children": { "RLTrainer._checkpoint": { "total": 0.21538542400048755, "count": 2, "self": 0.21538542400048755 } } }, "_update_policy": { "total": 588.0327613129912, "count": 437, "self": 350.96503967503804, "children": { "TorchPPOOptimizer.update": { "total": 237.06772163795313, "count": 22842, "self": 237.06772163795313 } } } } } } }, "trainer_threads": { "total": 1.442999746359419e-06, "count": 1, "self": 1.442999746359419e-06 }, "TrainerController._save_models": { "total": 0.09696871699998155, "count": 1, "self": 0.0015329709995057783, "children": { "RLTrainer._checkpoint": { "total": 0.09543574600047577, "count": 1, "self": 0.09543574600047577 } } } } } } }