{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5032625198364258, "min": 0.46880099177360535, "max": 1.4318139553070068, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15178.3984375, "min": 14124.0361328125, "max": 43435.5078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989906.0, "min": 29952.0, "max": 989906.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989906.0, "min": 29952.0, "max": 989906.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2829139232635498, "min": -0.08915776014328003, "max": 0.3036859631538391, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 73.5576171875, "min": -21.48702049255371, "max": 78.9583511352539, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.47804346680641174, "min": -0.47804346680641174, "max": 0.6832510828971863, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -124.29129791259766, "min": -124.29129791259766, "max": 176.27877807617188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0677675533974028, "min": 0.06556681446446519, "max": 0.07335611940530733, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9487457475636392, "min": 0.5084986085769314, "max": 1.075855270443557, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.06862552598803089, "min": 0.0007723174118143354, "max": 0.08587312920800674, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.9607573638324324, "min": 0.009267808941772024, "max": 1.2022238089120945, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.440590376978574e-06, "min": 7.440590376978574e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010416826527770003, "min": 0.00010416826527770003, "max": 0.0035070461309846994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248016428571428, "min": 0.10248016428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347223, "min": 1.3691136000000002, "max": 2.5690153, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025776841214285724, "min": 0.00025776841214285724, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003608757770000001, "min": 0.003608757770000001, "max": 0.11692462846999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011978588066995144, "min": 0.011978588066995144, "max": 0.5302184224128723, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16770023107528687, "min": 0.16770023107528687, "max": 3.711528778076172, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 566.6545454545454, "min": 540.2452830188679, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31166.0, "min": 15984.0, "max": 32663.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1059708775444463, "min": -1.0000000521540642, "max": 1.2285036738548014, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 60.82839826494455, "min": -32.000001668930054, "max": 66.33919838815928, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1059708775444463, "min": -1.0000000521540642, "max": 1.2285036738548014, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 60.82839826494455, "min": -32.000001668930054, "max": 66.33919838815928, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07091439356180755, "min": 0.07091439356180755, "max": 10.819158278405666, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.900291645899415, "min": 3.654805901227519, "max": 173.10653245449066, "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": "1688970486", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "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": "1688972640" }, "total": 2153.6783560549998, "count": 1, "self": 0.8388452799995321, "children": { "run_training.setup": { "total": 0.04208071800007929, "count": 1, "self": 0.04208071800007929 }, "TrainerController.start_learning": { "total": 2152.7974300570004, "count": 1, "self": 1.3003289770463198, "children": { "TrainerController._reset_env": { "total": 4.2991792360001, "count": 1, "self": 4.2991792360001 }, "TrainerController.advance": { "total": 2147.041225561954, "count": 63387, "self": 1.3312253799294922, "children": { "env_step": { "total": 1491.3476623810363, "count": 63387, "self": 1381.7969522651147, "children": { "SubprocessEnvManager._take_step": { "total": 108.7280757739909, "count": 63387, "self": 4.694905449024191, "children": { "TorchPolicy.evaluate": { "total": 104.0331703249667, "count": 62546, "self": 104.0331703249667 } } }, "workers": { "total": 0.8226343419307796, "count": 63387, "self": 0.0, "children": { "worker_root": { "total": 2148.083332702952, "count": 63387, "is_parallel": true, "self": 877.4335157429371, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020901370000956376, "count": 1, "is_parallel": true, "self": 0.0006495119996543508, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014406250004412868, "count": 8, "is_parallel": true, "self": 0.0014406250004412868 } } }, "UnityEnvironment.step": { "total": 0.053456848999985596, "count": 1, "is_parallel": true, "self": 0.0006380810000337078, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005892819999644416, "count": 1, "is_parallel": true, "self": 0.0005892819999644416 }, "communicator.exchange": { "total": 0.05014312399998744, "count": 1, "is_parallel": true, "self": 0.05014312399998744 }, "steps_from_proto": { "total": 0.0020863620000000083, "count": 1, "is_parallel": true, "self": 0.0003937339997719391, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016926280002280691, "count": 8, "is_parallel": true, "self": 0.0016926280002280691 } } } } } } }, "UnityEnvironment.step": { "total": 1270.6498169600147, "count": 63386, "is_parallel": true, "self": 34.496795796992046, "children": { "UnityEnvironment._generate_step_input": { "total": 23.475015314018492, "count": 63386, "is_parallel": true, "self": 23.475015314018492 }, "communicator.exchange": { "total": 1106.1990079959626, "count": 63386, "is_parallel": true, "self": 1106.1990079959626 }, "steps_from_proto": { "total": 106.47899785304162, "count": 63386, "is_parallel": true, "self": 20.336749796123286, "children": { "_process_rank_one_or_two_observation": { "total": 86.14224805691833, "count": 507088, "is_parallel": true, "self": 86.14224805691833 } } } } } } } } } } }, "trainer_advance": { "total": 654.3623378009881, "count": 63387, "self": 2.514689585985707, "children": { "process_trajectory": { "total": 109.42137213199953, "count": 63387, "self": 109.15173985699971, "children": { "RLTrainer._checkpoint": { "total": 0.2696322749998217, "count": 2, "self": 0.2696322749998217 } } }, "_update_policy": { "total": 542.4262760830029, "count": 447, "self": 348.1735523609739, "children": { "TorchPPOOptimizer.update": { "total": 194.25272372202903, "count": 22842, "self": 194.25272372202903 } } } } } } }, "trainer_threads": { "total": 1.36500011649332e-06, "count": 1, "self": 1.36500011649332e-06 }, "TrainerController._save_models": { "total": 0.1566949170000953, "count": 1, "self": 0.0019979379999313096, "children": { "RLTrainer._checkpoint": { "total": 0.154696979000164, "count": 1, "self": 0.154696979000164 } } } } } } }