{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.437661737203598, "min": 0.43379276990890503, "max": 1.4737204313278198, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13227.888671875, "min": 12992.9609375, "max": 44706.78125, "count": 33 }, "Pyramids.Step.mean": { "value": 989946.0, "min": 29928.0, "max": 989946.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989946.0, "min": 29928.0, "max": 989946.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.18656836450099945, "min": -0.1185806542634964, "max": 0.23137059807777405, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 47.20179748535156, "min": -28.577938079833984, "max": 58.99950408935547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017125345766544342, "min": -0.0001443738874513656, "max": 0.5250396132469177, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.332712650299072, "min": -0.035371601581573486, "max": 124.95943450927734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06651156819892652, "min": 0.0645668939273173, "max": 0.07304581741653324, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9311619547849712, "min": 0.6470986258641932, "max": 1.01213510000083, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00796599776851447, "min": 0.0005264793903165066, "max": 0.01093859747932262, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11152396875920258, "min": 0.006317752683798079, "max": 0.12477375389625746, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.575011760742857e-06, "min": 7.575011760742857e-06, "max": 0.00029479560173479994, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010605016465039999, "min": 0.00010605016465039999, "max": 0.0033318732893756, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252497142857143, "min": 0.10252497142857143, "max": 0.1982652, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353496000000001, "min": 1.4353496000000001, "max": 2.4861579000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026224464571428566, "min": 0.00026224464571428566, "max": 0.00982669348, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036714250399999993, "min": 0.0036714250399999993, "max": 0.11107137756000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008683050982654095, "min": 0.008683050982654095, "max": 0.3794618248939514, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12156271934509277, "min": 0.12156271934509277, "max": 3.415156364440918, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 605.0208333333334, "min": 605.0208333333334, "max": 993.6129032258065, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29041.0, "min": 16726.0, "max": 32800.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6447582989931107, "min": -0.9273667188982169, "max": 0.8708086713500645, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 30.94839835166931, "min": -29.391401648521423, "max": 40.057198882102966, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6447582989931107, "min": -0.9273667188982169, "max": 0.8708086713500645, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 30.94839835166931, "min": -29.391401648521423, "max": 40.057198882102966, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.053759676326687135, "min": 0.053759676326687135, "max": 7.876482967701223, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5804644636809826, "min": 2.5804644636809826, "max": 141.77669341862202, "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": "1703269488", "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": "1703271551" }, "total": 2062.3560006220005, "count": 1, "self": 0.49193265000030806, "children": { "run_training.setup": { "total": 0.044676068999933705, "count": 1, "self": 0.044676068999933705 }, "TrainerController.start_learning": { "total": 2061.819391903, "count": 1, "self": 1.3501089990190849, "children": { "TrainerController._reset_env": { "total": 1.98026269900015, "count": 1, "self": 1.98026269900015 }, "TrainerController.advance": { "total": 2058.4000495399805, "count": 63335, "self": 1.3891699649971088, "children": { "env_step": { "total": 1430.3859979219812, "count": 63335, "self": 1301.9389465831057, "children": { "SubprocessEnvManager._take_step": { "total": 127.64653741394022, "count": 63335, "self": 4.750308186013854, "children": { "TorchPolicy.evaluate": { "total": 122.89622922792637, "count": 62567, "self": 122.89622922792637 } } }, "workers": { "total": 0.8005139249353306, "count": 63335, "self": 0.0, "children": { "worker_root": { "total": 2056.8737207599834, "count": 63335, "is_parallel": true, "self": 871.2158931649535, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017723710000154824, "count": 1, "is_parallel": true, "self": 0.0005819020004764752, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011904689995390072, "count": 8, "is_parallel": true, "self": 0.0011904689995390072 } } }, "UnityEnvironment.step": { "total": 0.04835113999979512, "count": 1, "is_parallel": true, "self": 0.0005701509999198606, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004454669999631733, "count": 1, "is_parallel": true, "self": 0.0004454669999631733 }, "communicator.exchange": { "total": 0.04571595399988837, "count": 1, "is_parallel": true, "self": 0.04571595399988837 }, "steps_from_proto": { "total": 0.001619568000023719, "count": 1, "is_parallel": true, "self": 0.00032905999955801235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012905080004657066, "count": 8, "is_parallel": true, "self": 0.0012905080004657066 } } } } } } }, "UnityEnvironment.step": { "total": 1185.6578275950299, "count": 63334, "is_parallel": true, "self": 34.2308809279923, "children": { "UnityEnvironment._generate_step_input": { "total": 24.485609053998814, "count": 63334, "is_parallel": true, "self": 24.485609053998814 }, "communicator.exchange": { "total": 1028.7461908180387, "count": 63334, "is_parallel": true, "self": 1028.7461908180387 }, "steps_from_proto": { "total": 98.19514679500003, "count": 63334, "is_parallel": true, "self": 19.61654869500444, "children": { "_process_rank_one_or_two_observation": { "total": 78.57859809999559, "count": 506672, "is_parallel": true, "self": 78.57859809999559 } } } } } } } } } } }, "trainer_advance": { "total": 626.6248816530021, "count": 63335, "self": 2.7096181778913433, "children": { "process_trajectory": { "total": 125.5473717441148, "count": 63335, "self": 125.3510468741149, "children": { "RLTrainer._checkpoint": { "total": 0.1963248699998985, "count": 2, "self": 0.1963248699998985 } } }, "_update_policy": { "total": 498.367891730996, "count": 452, "self": 296.85403259293776, "children": { "TorchPPOOptimizer.update": { "total": 201.51385913805825, "count": 22803, "self": 201.51385913805825 } } } } } } }, "trainer_threads": { "total": 9.529999260848854e-07, "count": 1, "self": 9.529999260848854e-07 }, "TrainerController._save_models": { "total": 0.08896971200010739, "count": 1, "self": 0.0013742660003117635, "children": { "RLTrainer._checkpoint": { "total": 0.08759544599979563, "count": 1, "self": 0.08759544599979563 } } } } } } }