{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4738684892654419, "min": 0.46863439679145813, "max": 1.4954925775527954, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14125.072265625, "min": 14125.072265625, "max": 45367.26171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989902.0, "min": 29952.0, "max": 989902.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989902.0, "min": 29952.0, "max": 989902.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2727510333061218, "min": -0.08775092661380768, "max": 0.45689207315444946, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 70.64251708984375, "min": -21.147974014282227, "max": 121.07640075683594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.12530072033405304, "min": -0.12530072033405304, "max": 0.34522688388824463, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -32.45288848876953, "min": -32.45288848876953, "max": 81.81877136230469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06612780629005838, "min": 0.06595392962782086, "max": 0.07390375225110374, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9257892880608173, "min": 0.49569036253064275, "max": 1.0332799497900493, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015986503474171816, "min": 0.0006200104902077456, "max": 0.015986503474171816, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22381104863840542, "min": 0.006200104902077457, "max": 0.22381104863840542, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.429018952264286e-06, "min": 7.429018952264286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001040062653317, "min": 0.0001040062653317, "max": 0.0033821123726293, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247630714285716, "min": 0.10247630714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346683000000002, "min": 1.3886848, "max": 2.5273707000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002573830835714285, "min": 0.0002573830835714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036033631699999994, "min": 0.0036033631699999994, "max": 0.11276433293, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009293941780924797, "min": 0.009293941780924797, "max": 0.4463872015476227, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13011518120765686, "min": 0.13011518120765686, "max": 3.1247103214263916, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 546.3333333333334, "min": 461.3968253968254, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31141.0, "min": 15984.0, "max": 32721.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9972606880058136, "min": -1.0000000521540642, "max": 1.4141428344069966, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 55.84659852832556, "min": -31.998401656746864, "max": 89.09099856764078, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9972606880058136, "min": -1.0000000521540642, "max": 1.4141428344069966, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 55.84659852832556, "min": -31.998401656746864, "max": 89.09099856764078, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05310933481606688, "min": 0.05278538200969157, "max": 8.811007727868855, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9741227496997453, "min": 2.923802062694449, "max": 140.97612364590168, "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": "1739979328", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739981446" }, "total": 2117.1446891389996, "count": 1, "self": 0.6934253709996483, "children": { "run_training.setup": { "total": 0.023659230000021125, "count": 1, "self": 0.023659230000021125 }, "TrainerController.start_learning": { "total": 2116.4276045379997, "count": 1, "self": 1.238706747012202, "children": { "TrainerController._reset_env": { "total": 3.5598101830000815, "count": 1, "self": 3.5598101830000815 }, "TrainerController.advance": { "total": 2111.514160679987, "count": 63418, "self": 1.2721428979853044, "children": { "env_step": { "total": 1436.2377366190226, "count": 63418, "self": 1287.070024157007, "children": { "SubprocessEnvManager._take_step": { "total": 148.42683391805235, "count": 63418, "self": 4.420627973035835, "children": { "TorchPolicy.evaluate": { "total": 144.00620594501652, "count": 62547, "self": 144.00620594501652 } } }, "workers": { "total": 0.7408785439631629, "count": 63418, "self": 0.0, "children": { "worker_root": { "total": 2111.4527799510156, "count": 63418, "is_parallel": true, "self": 931.4932749810309, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005382901999951173, "count": 1, "is_parallel": true, "self": 0.004082772999822737, "children": { "_process_rank_one_or_two_observation": { "total": 0.001300129000128436, "count": 8, "is_parallel": true, "self": 0.001300129000128436 } } }, "UnityEnvironment.step": { "total": 0.0979492860000164, "count": 1, "is_parallel": true, "self": 0.0005453020000913966, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004515489999903366, "count": 1, "is_parallel": true, "self": 0.0004515489999903366 }, "communicator.exchange": { "total": 0.09517187899996316, "count": 1, "is_parallel": true, "self": 0.09517187899996316 }, "steps_from_proto": { "total": 0.0017805559999715115, "count": 1, "is_parallel": true, "self": 0.0004956280000669722, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012849279999045393, "count": 8, "is_parallel": true, "self": 0.0012849279999045393 } } } } } } }, "UnityEnvironment.step": { "total": 1179.9595049699847, "count": 63417, "is_parallel": true, "self": 31.43539356497695, "children": { "UnityEnvironment._generate_step_input": { "total": 22.452612583983296, "count": 63417, "is_parallel": true, "self": 22.452612583983296 }, "communicator.exchange": { "total": 1034.4649327870354, "count": 63417, "is_parallel": true, "self": 1034.4649327870354 }, "steps_from_proto": { "total": 91.60656603398922, "count": 63417, "is_parallel": true, "self": 18.05069803993092, "children": { "_process_rank_one_or_two_observation": { "total": 73.5558679940583, "count": 507336, "is_parallel": true, "self": 73.5558679940583 } } } } } } } } } } }, "trainer_advance": { "total": 674.0042811629792, "count": 63418, "self": 2.4072081820207814, "children": { "process_trajectory": { "total": 123.29947578196311, "count": 63418, "self": 122.96037284896306, "children": { "RLTrainer._checkpoint": { "total": 0.33910293300004923, "count": 2, "self": 0.33910293300004923 } } }, "_update_policy": { "total": 548.2975971989953, "count": 442, "self": 300.7177688979841, "children": { "TorchPPOOptimizer.update": { "total": 247.57982830101116, "count": 22827, "self": 247.57982830101116 } } } } } } }, "trainer_threads": { "total": 1.2810000953322742e-06, "count": 1, "self": 1.2810000953322742e-06 }, "TrainerController._save_models": { "total": 0.11492564700029106, "count": 1, "self": 0.0020180900005470903, "children": { "RLTrainer._checkpoint": { "total": 0.11290755699974397, "count": 1, "self": 0.11290755699974397 } } } } } } }