{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13767725229263306, "min": 0.11736847460269928, "max": 1.4065113067626953, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4145.7373046875, "min": 3506.031005859375, "max": 42667.92578125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999893.0, "min": 29952.0, "max": 2999893.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999893.0, "min": 29952.0, "max": 2999893.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8235560655593872, "min": -0.09233143925666809, "max": 0.8545447587966919, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 249.53749084472656, "min": -22.1595458984375, "max": 259.052001953125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.060299649834632874, "min": -0.03345511481165886, "max": 0.3823799788951874, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 18.270793914794922, "min": -9.802349090576172, "max": 92.9183349609375, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06712005015267633, "min": 0.06505776217037906, "max": 0.07593477028441173, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9396807021374686, "min": 0.5315433919908821, "max": 1.0888115173438564, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01675657390759337, "min": 0.0009381663753779158, "max": 0.017523056156711563, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23459203470630718, "min": 0.01313432925529082, "max": 0.2464741367233835, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4351280930857127e-06, "min": 1.4351280930857127e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0091793303199977e-05, "min": 2.0091793303199977e-05, "max": 0.004010773063075666, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047834285714287, "min": 0.10047834285714287, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066968000000002, "min": 1.3962282666666668, "max": 2.8275804, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.778645142857135e-05, "min": 5.778645142857135e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008090103199999989, "min": 0.0008090103199999989, "max": 0.1336987409, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013224425725638866, "min": 0.013007568195462227, "max": 0.5398194193840027, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18514196574687958, "min": 0.18210595846176147, "max": 3.778736114501953, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 207.41007194244605, "min": 207.41007194244605, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28830.0, "min": 15984.0, "max": 32857.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7649485568915095, "min": -1.0000000521540642, "max": 1.7738753476220628, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 247.09279796481133, "min": -28.120801649987698, "max": 247.09279796481133, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7649485568915095, "min": -1.0000000521540642, "max": 1.7738753476220628, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 247.09279796481133, "min": -28.120801649987698, "max": 247.09279796481133, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028046778935095062, "min": 0.028046778935095062, "max": 9.988997579552233, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9265490509133087, "min": 3.9265490509133087, "max": 159.82396127283573, "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": "1742648685", "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": "1742657080" }, "total": 8394.721010406, "count": 1, "self": 1.4242156300006172, "children": { "run_training.setup": { "total": 0.023512602999971932, "count": 1, "self": 0.023512602999971932 }, "TrainerController.start_learning": { "total": 8393.273282172999, "count": 1, "self": 4.931491036239095, "children": { "TrainerController._reset_env": { "total": 3.5326586170000382, "count": 1, "self": 3.5326586170000382 }, "TrainerController.advance": { "total": 8384.665987793762, "count": 195779, "self": 5.072668996564971, "children": { "env_step": { "total": 6171.229749677905, "count": 195779, "self": 5648.074184336097, "children": { "SubprocessEnvManager._take_step": { "total": 520.2704272579558, "count": 195779, "self": 15.971823155933237, "children": { "TorchPolicy.evaluate": { "total": 504.2986041020226, "count": 187559, "self": 504.2986041020226 } } }, "workers": { "total": 2.8851380838523255, "count": 195779, "self": 0.0, "children": { "worker_root": { "total": 8375.217938242642, "count": 195779, "is_parallel": true, "self": 3120.3453993627563, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005836607999981425, "count": 1, "is_parallel": true, "self": 0.004307386999926166, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015292210000552586, "count": 8, "is_parallel": true, "self": 0.0015292210000552586 } } }, "UnityEnvironment.step": { "total": 0.05865269499997794, "count": 1, "is_parallel": true, "self": 0.0005673469999578629, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005633929999930842, "count": 1, "is_parallel": true, "self": 0.0005633929999930842 }, "communicator.exchange": { "total": 0.052018168000017795, "count": 1, "is_parallel": true, "self": 0.052018168000017795 }, "steps_from_proto": { "total": 0.005503787000009197, "count": 1, "is_parallel": true, "self": 0.004223927000055028, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012798599999541693, "count": 8, "is_parallel": true, "self": 0.0012798599999541693 } } } } } } }, "UnityEnvironment.step": { "total": 5254.872538879886, "count": 195778, "is_parallel": true, "self": 105.91264481711005, "children": { "UnityEnvironment._generate_step_input": { "total": 78.69610648391279, "count": 195778, "is_parallel": true, "self": 78.69610648391279 }, "communicator.exchange": { "total": 4738.607032636858, "count": 195778, "is_parallel": true, "self": 4738.607032636858 }, "steps_from_proto": { "total": 331.6567549420054, "count": 195778, "is_parallel": true, "self": 69.50220483661946, "children": { "_process_rank_one_or_two_observation": { "total": 262.15455010538597, "count": 1566224, "is_parallel": true, "self": 262.15455010538597 } } } } } } } } } } }, "trainer_advance": { "total": 2208.3635691192926, "count": 195779, "self": 9.606010087308277, "children": { "process_trajectory": { "total": 436.6751568659881, "count": 195779, "self": 435.9109330989888, "children": { "RLTrainer._checkpoint": { "total": 0.7642237669992937, "count": 6, "self": 0.7642237669992937 } } }, "_update_policy": { "total": 1762.0824021659964, "count": 1406, "self": 968.5204899701068, "children": { "TorchPPOOptimizer.update": { "total": 793.5619121958896, "count": 68364, "self": 793.5619121958896 } } } } } } }, "trainer_threads": { "total": 1.4139986888039857e-06, "count": 1, "self": 1.4139986888039857e-06 }, "TrainerController._save_models": { "total": 0.14314331199966546, "count": 1, "self": 0.0025536149987601675, "children": { "RLTrainer._checkpoint": { "total": 0.1405896970009053, "count": 1, "self": 0.1405896970009053 } } } } } } }