{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5890570878982544, "min": 0.5806085467338562, "max": 1.4019008874893188, "count": 30 }, "Pyramids.Policy.Entropy.sum": { "value": 17558.61328125, "min": 17511.154296875, "max": 42528.06640625, "count": 30 }, "Pyramids.Step.mean": { "value": 899917.0, "min": 29930.0, "max": 899917.0, "count": 30 }, "Pyramids.Step.sum": { "value": 899917.0, "min": 29930.0, "max": 899917.0, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3437330424785614, "min": -0.1108439713716507, "max": 0.35709699988365173, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 89.02685546875, "min": -26.270021438598633, "max": 94.27360534667969, "count": 30 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015149506740272045, "min": 0.015149506740272045, "max": 0.38376158475875854, "count": 30 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.923722267150879, "min": 3.7801356315612793, "max": 92.48654174804688, "count": 30 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06951294143477248, "min": 0.06556993023151954, "max": 0.07337778122950193, "count": 30 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0426941215215872, "min": 0.5095945363242083, "max": 1.0585052202804945, "count": 30 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011598017428993258, "min": 0.00011223956655982646, "max": 0.01402242299586416, "count": 30 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17397026143489888, "min": 0.0014591143652777439, "max": 0.19631392194209824, "count": 30 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00021150075616642447, "min": 0.00021150075616642447, "max": 0.00029838354339596195, "count": 30 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.003172511342496367, "min": 0.0020886848037717336, "max": 0.0039690189769937, "count": 30 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.17050024222222224, "min": 0.17050024222222224, "max": 0.19946118095238097, "count": 30 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.5575036333333334, "min": 1.3962282666666668, "max": 2.7824799333333328, "count": 30 }, "Pyramids.Policy.Beta.mean": { "value": 0.007052974197999998, "min": 0.007052974197999998, "max": 0.009946171977142856, "count": 30 }, "Pyramids.Policy.Beta.sum": { "value": 0.10579461296999998, "min": 0.06962320384, "max": 0.13230832936999998, "count": 30 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01331007108092308, "min": 0.01331007108092308, "max": 0.7081205248832703, "count": 30 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1996510624885559, "min": 0.1949319839477539, "max": 4.956843852996826, "count": 30 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 499.2105263157895, "min": 481.1875, "max": 999.0, "count": 30 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28455.0, "min": 16857.0, "max": 32992.0, "count": 30 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.29020698682258, "min": -0.9999125520698726, "max": 1.3625155973713845, "count": 30 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 73.54179824888706, "min": -31.997201666235924, "max": 87.20099823176861, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.29020698682258, "min": -0.9999125520698726, "max": 1.3625155973713845, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 73.54179824888706, "min": -31.997201666235924, "max": 87.20099823176861, "count": 30 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06815119140185089, "min": 0.06815119140185089, "max": 13.717725730994168, "count": 30 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8846179099055007, "min": 3.8846179099055007, "max": 233.20133742690086, "count": 30 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1712527565", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712529491" }, "total": 1926.3899368959997, "count": 1, "self": 0.38069954899947334, "children": { "run_training.setup": { "total": 0.08702658400034124, "count": 1, "self": 0.08702658400034124 }, "TrainerController.start_learning": { "total": 1925.9222107629998, "count": 1, "self": 1.2907312730385456, "children": { "TrainerController._reset_env": { "total": 2.3211664730001758, "count": 1, "self": 2.3211664730001758 }, "TrainerController.advance": { "total": 1922.1589925839608, "count": 57373, "self": 1.3277347779026059, "children": { "env_step": { "total": 1351.3449430410437, "count": 57373, "self": 1229.0939210409515, "children": { "SubprocessEnvManager._take_step": { "total": 121.45048265507648, "count": 57373, "self": 4.293766252113983, "children": { "TorchPolicy.evaluate": { "total": 117.1567164029625, "count": 56583, "self": 117.1567164029625 } } }, "workers": { "total": 0.8005393450157499, "count": 57372, "self": 0.0, "children": { "worker_root": { "total": 1921.4094024200226, "count": 57372, "is_parallel": true, "self": 805.1252596150844, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002207309999903373, "count": 1, "is_parallel": true, "self": 0.0006673160005448153, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015399939993585576, "count": 8, "is_parallel": true, "self": 0.0015399939993585576 } } }, "UnityEnvironment.step": { "total": 0.04839418100027615, "count": 1, "is_parallel": true, "self": 0.0006944440006009245, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004506309996941127, "count": 1, "is_parallel": true, "self": 0.0004506309996941127 }, "communicator.exchange": { "total": 0.04533611699980611, "count": 1, "is_parallel": true, "self": 0.04533611699980611 }, "steps_from_proto": { "total": 0.0019129890001750027, "count": 1, "is_parallel": true, "self": 0.0003753570003937057, "children": { "_process_rank_one_or_two_observation": { "total": 0.001537631999781297, "count": 8, "is_parallel": true, "self": 0.001537631999781297 } } } } } } }, "UnityEnvironment.step": { "total": 1116.2841428049383, "count": 57371, "is_parallel": true, "self": 32.07215328902976, "children": { "UnityEnvironment._generate_step_input": { "total": 21.545949239936363, "count": 57371, "is_parallel": true, "self": 21.545949239936363 }, "communicator.exchange": { "total": 970.6019852459776, "count": 57371, "is_parallel": true, "self": 970.6019852459776 }, "steps_from_proto": { "total": 92.0640550299945, "count": 57371, "is_parallel": true, "self": 18.693467616030375, "children": { "_process_rank_one_or_two_observation": { "total": 73.37058741396413, "count": 458968, "is_parallel": true, "self": 73.37058741396413 } } } } } } } } } } }, "trainer_advance": { "total": 569.4863147650144, "count": 57372, "self": 2.4730959570388222, "children": { "process_trajectory": { "total": 111.68641964897415, "count": 57372, "self": 111.57511701097383, "children": { "RLTrainer._checkpoint": { "total": 0.1113026380003248, "count": 1, "self": 0.1113026380003248 } } }, "_update_policy": { "total": 455.32679915900144, "count": 402, "self": 266.89855077501215, "children": { "TorchPPOOptimizer.update": { "total": 188.42824838398928, "count": 20688, "self": 188.42824838398928 } } } } } } }, "trainer_threads": { "total": 1.3879998732591048e-06, "count": 1, "self": 1.3879998732591048e-06 }, "TrainerController._save_models": { "total": 0.15131904500049131, "count": 1, "self": 0.002407309000773239, "children": { "RLTrainer._checkpoint": { "total": 0.14891173599971808, "count": 1, "self": 0.14891173599971808 } } } } } } }