{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43915560841560364, "min": 0.43915560841560364, "max": 1.4234611988067627, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13146.5625, "min": 13146.5625, "max": 43182.1171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.516571044921875, "min": -0.08865094184875488, "max": 0.5249823331832886, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 143.60675048828125, "min": -21.276226043701172, "max": 145.42010498046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.057158518582582474, "min": -0.017699720337986946, "max": 0.4814152419567108, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 15.890068054199219, "min": -4.690425872802734, "max": 114.09541320800781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06509863779776626, "min": 0.06421051919480678, "max": 0.07464485454703958, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9764795669664939, "min": 0.5114945926577731, "max": 1.0511575324247437, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01553486914943076, "min": 0.0001456282720922591, "max": 0.017217206227498887, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2330230372414614, "min": 0.002038795809291627, "max": 0.2410408871849844, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.491377502906662e-06, "min": 7.491377502906662e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011237066254359994, "min": 0.00011237066254359994, "max": 0.0035076620307794, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249709333333334, "min": 0.10249709333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374564000000002, "min": 1.3691136000000002, "max": 2.5692206, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025945962399999986, "min": 0.00025945962399999986, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003891894359999998, "min": 0.003891894359999998, "max": 0.11694513794, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012437420897185802, "min": 0.012437420897185802, "max": 0.44716331362724304, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18656131625175476, "min": 0.18006260693073273, "max": 3.130143165588379, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 357.6588235294118, "min": 354.7674418604651, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30401.0, "min": 15984.0, "max": 32294.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6165237897740943, "min": -1.0000000521540642, "max": 1.620530843918706, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.78799834102392, "min": -32.000001668930054, "max": 135.78799834102392, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6165237897740943, "min": -1.0000000521540642, "max": 1.620530843918706, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.78799834102392, "min": -32.000001668930054, "max": 135.78799834102392, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04647597727792648, "min": 0.04647597727792648, "max": 9.092697262763977, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9039820913458243, "min": 3.9039820913458243, "max": 145.48315620422363, "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": "1686118762", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1686121017" }, "total": 2255.1028320309997, "count": 1, "self": 0.47591283099973225, "children": { "run_training.setup": { "total": 0.0366336299998693, "count": 1, "self": 0.0366336299998693 }, "TrainerController.start_learning": { "total": 2254.59028557, "count": 1, "self": 1.5666082909478973, "children": { "TrainerController._reset_env": { "total": 5.063071235999814, "count": 1, "self": 5.063071235999814 }, "TrainerController.advance": { "total": 2247.8638521460525, "count": 63705, "self": 1.5537499131901313, "children": { "env_step": { "total": 1588.766362417879, "count": 63705, "self": 1472.0924524337556, "children": { "SubprocessEnvManager._take_step": { "total": 115.77020215704897, "count": 63705, "self": 4.9658996420444055, "children": { "TorchPolicy.evaluate": { "total": 110.80430251500457, "count": 62555, "self": 110.80430251500457 } } }, "workers": { "total": 0.9037078270744132, "count": 63705, "self": 0.0, "children": { "worker_root": { "total": 2248.993563313996, "count": 63705, "is_parallel": true, "self": 896.7022219069768, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025155490002362058, "count": 1, "is_parallel": true, "self": 0.0006804409999858763, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018351080002503295, "count": 8, "is_parallel": true, "self": 0.0018351080002503295 } } }, "UnityEnvironment.step": { "total": 0.07674503699990964, "count": 1, "is_parallel": true, "self": 0.0006662979999418894, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005023429998800566, "count": 1, "is_parallel": true, "self": 0.0005023429998800566 }, "communicator.exchange": { "total": 0.07351763499991648, "count": 1, "is_parallel": true, "self": 0.07351763499991648 }, "steps_from_proto": { "total": 0.0020587610001712164, "count": 1, "is_parallel": true, "self": 0.00042051599939441076, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016382450007768057, "count": 8, "is_parallel": true, "self": 0.0016382450007768057 } } } } } } }, "UnityEnvironment.step": { "total": 1352.2913414070194, "count": 63704, "is_parallel": true, "self": 34.55258667493763, "children": { "UnityEnvironment._generate_step_input": { "total": 22.889135044054456, "count": 63704, "is_parallel": true, "self": 22.889135044054456 }, "communicator.exchange": { "total": 1189.6145849770123, "count": 63704, "is_parallel": true, "self": 1189.6145849770123 }, "steps_from_proto": { "total": 105.23503471101503, "count": 63704, "is_parallel": true, "self": 21.060295321027752, "children": { "_process_rank_one_or_two_observation": { "total": 84.17473938998728, "count": 509632, "is_parallel": true, "self": 84.17473938998728 } } } } } } } } } } }, "trainer_advance": { "total": 657.5437398149834, "count": 63705, "self": 2.8623747060014466, "children": { "process_trajectory": { "total": 109.40628894397696, "count": 63705, "self": 109.16081514297684, "children": { "RLTrainer._checkpoint": { "total": 0.2454738010001165, "count": 2, "self": 0.2454738010001165 } } }, "_update_policy": { "total": 545.275076165005, "count": 447, "self": 351.2921764690236, "children": { "TorchPPOOptimizer.update": { "total": 193.98289969598136, "count": 22803, "self": 193.98289969598136 } } } } } } }, "trainer_threads": { "total": 8.580000212532468e-07, "count": 1, "self": 8.580000212532468e-07 }, "TrainerController._save_models": { "total": 0.0967530389998501, "count": 1, "self": 0.0015374720005638665, "children": { "RLTrainer._checkpoint": { "total": 0.09521556699928624, "count": 1, "self": 0.09521556699928624 } } } } } } }