{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30677956342697144, "min": 0.30677956342697144, "max": 1.4612200260162354, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9144.4853515625, "min": 9144.4853515625, "max": 44327.5703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5125426054000854, "min": -0.24414397776126862, "max": 0.5304714441299438, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.48684692382812, "min": -57.86212158203125, "max": 146.9405975341797, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012977099046111107, "min": -0.002229227451607585, "max": 0.3259146511554718, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.607633590698242, "min": -0.6041206121444702, "max": 78.21951293945312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07055453636331506, "min": 0.06571497830390442, "max": 0.07609109733572376, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9877635090864108, "min": 0.4800928720467437, "max": 1.0617340138597486, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015531677520595534, "min": 0.0010772303194386036, "max": 0.01569277814206118, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21744348528833748, "min": 0.0075406122360702245, "max": 0.2212044810003135, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.695354577771433e-06, "min": 7.695354577771433e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010773496408880007, "min": 0.00010773496408880007, "max": 0.0036342379885873997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256508571428571, "min": 0.10256508571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359112, "min": 1.3691136000000002, "max": 2.6172849, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000266252062857143, "min": 0.000266252062857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003727528880000002, "min": 0.003727528880000002, "max": 0.12116011874, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010110179893672466, "min": 0.010110179893672466, "max": 0.4666884243488312, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14154252409934998, "min": 0.14154252409934998, "max": 3.2668190002441406, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 342.2125, "min": 337.45348837209303, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27377.0, "min": 15984.0, "max": 32777.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6077724866569043, "min": -1.0000000521540642, "max": 1.6077724866569043, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 128.62179893255234, "min": -32.000001668930054, "max": 135.2117983996868, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6077724866569043, "min": -1.0000000521540642, "max": 1.6077724866569043, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 128.62179893255234, "min": -32.000001668930054, "max": 135.2117983996868, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03609340039147355, "min": 0.03609340039147355, "max": 9.22411336004734, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.887472031317884, "min": 2.887472031317884, "max": 147.58581376075745, "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": "1706663091", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706665264" }, "total": 2173.721051545, "count": 1, "self": 0.5443238149996432, "children": { "run_training.setup": { "total": 0.04947695200007729, "count": 1, "self": 0.04947695200007729 }, "TrainerController.start_learning": { "total": 2173.1272507780004, "count": 1, "self": 1.3722001740611631, "children": { "TrainerController._reset_env": { "total": 2.3423597080000036, "count": 1, "self": 2.3423597080000036 }, "TrainerController.advance": { "total": 2169.3260346829397, "count": 63825, "self": 1.3996063580320879, "children": { "env_step": { "total": 1542.6310562739818, "count": 63825, "self": 1415.67522473595, "children": { "SubprocessEnvManager._take_step": { "total": 126.15447936405144, "count": 63825, "self": 4.563255502009724, "children": { "TorchPolicy.evaluate": { "total": 121.59122386204172, "count": 62547, "self": 121.59122386204172 } } }, "workers": { "total": 0.8013521739803764, "count": 63825, "self": 0.0, "children": { "worker_root": { "total": 2167.9519243600366, "count": 63825, "is_parallel": true, "self": 866.230318356093, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019981320001534186, "count": 1, "is_parallel": true, "self": 0.0006526009997287474, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013455310004246712, "count": 8, "is_parallel": true, "self": 0.0013455310004246712 } } }, "UnityEnvironment.step": { "total": 0.04793188299981921, "count": 1, "is_parallel": true, "self": 0.0006482049998339789, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046655400001327507, "count": 1, "is_parallel": true, "self": 0.00046655400001327507 }, "communicator.exchange": { "total": 0.045230736000121397, "count": 1, "is_parallel": true, "self": 0.045230736000121397 }, "steps_from_proto": { "total": 0.0015863879998505581, "count": 1, "is_parallel": true, "self": 0.0003444929998295265, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012418950000210316, "count": 8, "is_parallel": true, "self": 0.0012418950000210316 } } } } } } }, "UnityEnvironment.step": { "total": 1301.7216060039436, "count": 63824, "is_parallel": true, "self": 34.98069977024625, "children": { "UnityEnvironment._generate_step_input": { "total": 24.086404731941457, "count": 63824, "is_parallel": true, "self": 24.086404731941457 }, "communicator.exchange": { "total": 1144.415338679929, "count": 63824, "is_parallel": true, "self": 1144.415338679929 }, "steps_from_proto": { "total": 98.239162821827, "count": 63824, "is_parallel": true, "self": 19.332695075569973, "children": { "_process_rank_one_or_two_observation": { "total": 78.90646774625702, "count": 510592, "is_parallel": true, "self": 78.90646774625702 } } } } } } } } } } }, "trainer_advance": { "total": 625.2953720509258, "count": 63825, "self": 2.6220743879280235, "children": { "process_trajectory": { "total": 124.58916800199131, "count": 63825, "self": 124.39484328399158, "children": { "RLTrainer._checkpoint": { "total": 0.19432471799973428, "count": 2, "self": 0.19432471799973428 } } }, "_update_policy": { "total": 498.0841296610065, "count": 449, "self": 292.6626478650069, "children": { "TorchPPOOptimizer.update": { "total": 205.42148179599963, "count": 22785, "self": 205.42148179599963 } } } } } } }, "trainer_threads": { "total": 9.019995559356175e-07, "count": 1, "self": 9.019995559356175e-07 }, "TrainerController._save_models": { "total": 0.0866553109999586, "count": 1, "self": 0.0013649600005010143, "children": { "RLTrainer._checkpoint": { "total": 0.08529035099945759, "count": 1, "self": 0.08529035099945759 } } } } } } }