{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18968354165554047, "min": 0.1755959391593933, "max": 1.488650918006897, "count": 69 }, "Pyramids.Policy.Entropy.sum": { "value": 5708.7158203125, "min": 5279.1162109375, "max": 45159.71484375, "count": 69 }, "Pyramids.Step.mean": { "value": 2069951.0, "min": 29952.0, "max": 2069951.0, "count": 69 }, "Pyramids.Step.sum": { "value": 2069951.0, "min": 29952.0, "max": 2069951.0, "count": 69 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8148035407066345, "min": -0.09488106518983841, "max": 0.8228468894958496, "count": 69 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 246.88546752929688, "min": -22.82662582397461, "max": 250.74118041992188, "count": 69 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01773555763065815, "min": -0.026374325156211853, "max": 0.37354576587677, "count": 69 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.373874187469482, "min": -7.64855432510376, "max": 88.53034973144531, "count": 69 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06496373595326163, "min": 0.06472064311771343, "max": 0.07432566444313633, "count": 69 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9094923033456629, "min": 0.5202796511019543, "max": 1.1054783891852233, "count": 69 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012761120731565392, "min": 0.0002604049990297676, "max": 0.016528935115738753, "count": 69 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1786556902419155, "min": 0.002604049990297676, "max": 0.23261369204071045, "count": 69 }, "Pyramids.Policy.LearningRate.mean": { "value": 9.442926852359998e-05, "min": 9.442926852359998e-05, "max": 0.00029838354339596195, "count": 69 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0013220097593303996, "min": 0.0013220097593303996, "max": 0.004027772457409233, "count": 69 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.13147640000000002, "min": 0.13147640000000002, "max": 0.19946118095238097, "count": 69 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.8406696000000002, "min": 1.3962282666666668, "max": 2.8425907666666665, "count": 69 }, "Pyramids.Policy.Beta.mean": { "value": 0.00315449236, "min": 0.00315449236, "max": 0.009946171977142856, "count": 69 }, "Pyramids.Policy.Beta.sum": { "value": 0.04416289304, "min": 0.04416289304, "max": 0.13427481758999998, "count": 69 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008442183956503868, "min": 0.007369266357272863, "max": 0.3536679148674011, "count": 69 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11819057166576385, "min": 0.10316973179578781, "max": 2.475675344467163, "count": 69 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 232.97744360902254, "min": 217.27007299270073, "max": 999.0, "count": 69 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30986.0, "min": 15984.0, "max": 33244.0, "count": 69 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.752616652259321, "min": -1.0000000521540642, "max": 1.7681284558816548, "count": 69 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 231.34539809823036, "min": -31.998401656746864, "max": 242.2335984557867, "count": 69 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.752616652259321, "min": -1.0000000521540642, "max": 1.7681284558816548, "count": 69 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 231.34539809823036, "min": -31.998401656746864, "max": 242.2335984557867, "count": 69 }, "Pyramids.Policy.RndReward.mean": { "value": 0.020492130744638747, "min": 0.019907757191855908, "max": 6.795010124333203, "count": 69 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7049612582923146, "min": 2.219608664920088, "max": 108.72016198933125, "count": 69 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 69 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 69 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704867424", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704872692" }, "total": 5267.881148627001, "count": 1, "self": 0.33894925500135287, "children": { "run_training.setup": { "total": 0.05402938999986873, "count": 1, "self": 0.05402938999986873 }, "TrainerController.start_learning": { "total": 5267.488169982, "count": 1, "self": 3.289797792961508, "children": { "TrainerController._reset_env": { "total": 2.676654252999924, "count": 1, "self": 2.676654252999924 }, "TrainerController.advance": { "total": 5261.388628928038, "count": 134176, "self": 3.3574123511752987, "children": { "env_step": { "total": 3897.98559204801, "count": 134176, "self": 3602.5180529010786, "children": { "SubprocessEnvManager._take_step": { "total": 293.4263240859941, "count": 134176, "self": 10.634103851944474, "children": { "TorchPolicy.evaluate": { "total": 282.79222023404964, "count": 129600, "self": 282.79222023404964 } } }, "workers": { "total": 2.0412150609372475, "count": 134175, "self": 0.0, "children": { "worker_root": { "total": 5255.301998365187, "count": 134175, "is_parallel": true, "self": 1930.876381950986, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024066099999799917, "count": 1, "is_parallel": true, "self": 0.0006730119989697414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017335980010102503, "count": 8, "is_parallel": true, "self": 0.0017335980010102503 } } }, "UnityEnvironment.step": { "total": 0.05946125399987068, "count": 1, "is_parallel": true, "self": 0.0005948289999651024, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004888270000265038, "count": 1, "is_parallel": true, "self": 0.0004888270000265038 }, "communicator.exchange": { "total": 0.056643485999757104, "count": 1, "is_parallel": true, "self": 0.056643485999757104 }, "steps_from_proto": { "total": 0.0017341120001219679, "count": 1, "is_parallel": true, "self": 0.0003462690001470037, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013878429999749642, "count": 8, "is_parallel": true, "self": 0.0013878429999749642 } } } } } } }, "UnityEnvironment.step": { "total": 3324.4256164142007, "count": 134174, "is_parallel": true, "self": 76.52160039914042, "children": { "UnityEnvironment._generate_step_input": { "total": 55.4744102419927, "count": 134174, "is_parallel": true, "self": 55.4744102419927 }, "communicator.exchange": { "total": 2965.843675842068, "count": 134174, "is_parallel": true, "self": 2965.843675842068 }, "steps_from_proto": { "total": 226.58592993099955, "count": 134174, "is_parallel": true, "self": 47.414576585091254, "children": { "_process_rank_one_or_two_observation": { "total": 179.1713533459083, "count": 1073392, "is_parallel": true, "self": 179.1713533459083 } } } } } } } } } } }, "trainer_advance": { "total": 1360.0456245288533, "count": 134175, "self": 6.41966488498565, "children": { "process_trajectory": { "total": 286.37858654085676, "count": 134175, "self": 285.9974531978569, "children": { "RLTrainer._checkpoint": { "total": 0.381133342999874, "count": 4, "self": 0.381133342999874 } } }, "_update_policy": { "total": 1067.247373103011, "count": 956, "self": 636.0507327511059, "children": { "TorchPPOOptimizer.update": { "total": 431.196640351905, "count": 47256, "self": 431.196640351905 } } } } } } }, "trainer_threads": { "total": 1.401000190526247e-06, "count": 1, "self": 1.401000190526247e-06 }, "TrainerController._save_models": { "total": 0.13308760699965205, "count": 1, "self": 0.0020231939997756854, "children": { "RLTrainer._checkpoint": { "total": 0.13106441299987637, "count": 1, "self": 0.13106441299987637 } } } } } } }