{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6197751760482788, "min": 0.5489454865455627, "max": 1.410788655281067, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18642.837890625, "min": 16380.533203125, "max": 42797.68359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36492422223091125, "min": -0.10509465634822845, "max": 0.4033730924129486, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 95.97506713867188, "min": -25.432907104492188, "max": 106.49049377441406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.1968708038330078, "min": -0.006282219663262367, "max": 1.3172565698623657, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 314.7770080566406, "min": -1.608248233795166, "max": 347.7557373046875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07212331990290077, "min": 0.06446217450118266, "max": 0.0721560926023681, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0097264786406108, "min": 0.5050926482165767, "max": 1.0299385108234014, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.1477399760070035, "min": 0.00013834467751267442, "max": 0.19651180597073917, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 2.068359664098049, "min": 0.001936825485177442, "max": 2.9476770895610875, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.318276132035714e-06, "min": 7.318276132035714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001024558658485, "min": 0.0001024558658485, "max": 0.0036353566882144995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243939285714286, "min": 0.10243939285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341515, "min": 1.3886848, "max": 2.6117855000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025369534642857145, "min": 0.00025369534642857145, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035517348500000005, "min": 0.0035517348500000005, "max": 0.12119737145000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014164499007165432, "min": 0.014164499007165432, "max": 0.5924299359321594, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1983029842376709, "min": 0.1983029842376709, "max": 4.147009372711182, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 438.71014492753625, "min": 438.71014492753625, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30271.0, "min": 15984.0, "max": 32504.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.387321718469046, "min": -1.0000000521540642, "max": 1.387321718469046, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 95.72519857436419, "min": -31.990801632404327, "max": 95.72519857436419, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.387321718469046, "min": -1.0000000521540642, "max": 1.387321718469046, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 95.72519857436419, "min": -31.990801632404327, "max": 95.72519857436419, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06458892425744915, "min": 0.06458892425744915, "max": 12.090948211029172, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.456635773763992, "min": 4.456635773763992, "max": 193.45517137646675, "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": "1690752307", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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 --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690754486" }, "total": 2178.94051907, "count": 1, "self": 0.47476738699970156, "children": { "run_training.setup": { "total": 0.031715505999954985, "count": 1, "self": 0.031715505999954985 }, "TrainerController.start_learning": { "total": 2178.434036177, "count": 1, "self": 1.3792267628759873, "children": { "TrainerController._reset_env": { "total": 4.176984629000117, "count": 1, "self": 4.176984629000117 }, "TrainerController.advance": { "total": 2172.7843921591234, "count": 63528, "self": 1.3681047421591757, "children": { "env_step": { "total": 1505.8298922420463, "count": 63528, "self": 1397.0445768620239, "children": { "SubprocessEnvManager._take_step": { "total": 107.92973749898601, "count": 63528, "self": 4.751400272946967, "children": { "TorchPolicy.evaluate": { "total": 103.17833722603905, "count": 62556, "self": 103.17833722603905 } } }, "workers": { "total": 0.8555778810364245, "count": 63528, "self": 0.0, "children": { "worker_root": { "total": 2173.5630106449835, "count": 63528, "is_parallel": true, "self": 890.903663762012, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001875214999927266, "count": 1, "is_parallel": true, "self": 0.0006242789995667408, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012509360003605252, "count": 8, "is_parallel": true, "self": 0.0012509360003605252 } } }, "UnityEnvironment.step": { "total": 0.04671306599993841, "count": 1, "is_parallel": true, "self": 0.0005976079996798944, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048337000021092535, "count": 1, "is_parallel": true, "self": 0.00048337000021092535 }, "communicator.exchange": { "total": 0.04364981200001239, "count": 1, "is_parallel": true, "self": 0.04364981200001239 }, "steps_from_proto": { "total": 0.001982276000035199, "count": 1, "is_parallel": true, "self": 0.0004097929997897154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015724830002454837, "count": 8, "is_parallel": true, "self": 0.0015724830002454837 } } } } } } }, "UnityEnvironment.step": { "total": 1282.6593468829715, "count": 63527, "is_parallel": true, "self": 34.28344006895736, "children": { "UnityEnvironment._generate_step_input": { "total": 22.692688406010802, "count": 63527, "is_parallel": true, "self": 22.692688406010802 }, "communicator.exchange": { "total": 1123.8218124490666, "count": 63527, "is_parallel": true, "self": 1123.8218124490666 }, "steps_from_proto": { "total": 101.86140595893676, "count": 63527, "is_parallel": true, "self": 20.267730194039586, "children": { "_process_rank_one_or_two_observation": { "total": 81.59367576489717, "count": 508216, "is_parallel": true, "self": 81.59367576489717 } } } } } } } } } } }, "trainer_advance": { "total": 665.5863951749177, "count": 63528, "self": 2.6532381659233124, "children": { "process_trajectory": { "total": 109.34126424799842, "count": 63528, "self": 109.12967378199846, "children": { "RLTrainer._checkpoint": { "total": 0.21159046599996145, "count": 2, "self": 0.21159046599996145 } } }, "_update_policy": { "total": 553.591892760996, "count": 452, "self": 362.31414863598934, "children": { "TorchPPOOptimizer.update": { "total": 191.27774412500662, "count": 22770, "self": 191.27774412500662 } } } } } } }, "trainer_threads": { "total": 9.420000424142927e-07, "count": 1, "self": 9.420000424142927e-07 }, "TrainerController._save_models": { "total": 0.09343168400027935, "count": 1, "self": 0.001566496000123152, "children": { "RLTrainer._checkpoint": { "total": 0.0918651880001562, "count": 1, "self": 0.0918651880001562 } } } } } } }