{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5708006024360657, "min": 0.42833226919174194, "max": 1.4708755016326904, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17324.939453125, "min": 12884.234375, "max": 44620.48046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.023499079048633575, "min": -0.10472418367862701, "max": 0.11422563344240189, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -5.686777114868164, "min": -25.133804321289062, "max": 27.071475982666016, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02088215947151184, "min": 0.018395602703094482, "max": 0.4636871814727783, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.053482532501221, "min": 4.525318145751953, "max": 111.74861145019531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06973046125535637, "min": 0.0627924472210939, "max": 0.07401389274539621, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9762264575749892, "min": 0.511833665656306, "max": 1.02404184554368, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0032879300028694045, "min": 5.180696372184087e-05, "max": 0.011883177638444407, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.046031020040171663, "min": 0.0007252974921057721, "max": 0.09525299894220571, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.550647483150001e-06, "min": 7.550647483150001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010570906476410001, "min": 0.00010570906476410001, "max": 0.0033754576748475, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251684999999999, "min": 0.10251684999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352359, "min": 1.3886848, "max": 2.4251525, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026143331500000003, "min": 0.00026143331500000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00366006641, "min": 0.00366006641, "max": 0.11253273475000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02031579241156578, "min": 0.02010221965610981, "max": 0.6815212965011597, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.28442108631134033, "min": 0.28143107891082764, "max": 4.770648956298828, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 903.0909090909091, "min": 827.027027027027, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29802.0, "min": 15984.0, "max": 33131.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.4793030714446848, "min": -1.0000000521540642, "max": -0.01655139451896822, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -15.817001357674599, "min": -30.139001734554768, "max": -0.6124015972018242, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.4793030714446848, "min": -1.0000000521540642, "max": -0.01655139451896822, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -15.817001357674599, "min": -30.139001734554768, "max": -0.6124015972018242, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1911653084680438, "min": 0.1789688714182105, "max": 14.141306975856423, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.3084551794454455, "min": 5.90584307257086, "max": 226.26091161370277, "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": "1703312035", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/rlunit5_pyramid_config.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": "1703314083" }, "total": 2048.0643324380003, "count": 1, "self": 0.8068657950002489, "children": { "run_training.setup": { "total": 0.05525127999999313, "count": 1, "self": 0.05525127999999313 }, "TrainerController.start_learning": { "total": 2047.202215363, "count": 1, "self": 1.426885606002088, "children": { "TrainerController._reset_env": { "total": 3.5284362290000217, "count": 1, "self": 3.5284362290000217 }, "TrainerController.advance": { "total": 2042.1278393359976, "count": 63230, "self": 1.4607886760625206, "children": { "env_step": { "total": 1403.2713328229486, "count": 63230, "self": 1272.5895367218998, "children": { "SubprocessEnvManager._take_step": { "total": 129.86931852602578, "count": 63230, "self": 4.663532566035769, "children": { "TorchPolicy.evaluate": { "total": 125.20578595999001, "count": 62576, "self": 125.20578595999001 } } }, "workers": { "total": 0.812477575023081, "count": 63230, "self": 0.0, "children": { "worker_root": { "total": 2042.0379567009934, "count": 63230, "is_parallel": true, "self": 887.171282867042, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007601380999972207, "count": 1, "is_parallel": true, "self": 0.0035518930000080218, "children": { "_process_rank_one_or_two_observation": { "total": 0.004049487999964185, "count": 8, "is_parallel": true, "self": 0.004049487999964185 } } }, "UnityEnvironment.step": { "total": 0.06000419200000806, "count": 1, "is_parallel": true, "self": 0.000649699000007331, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000496616000020822, "count": 1, "is_parallel": true, "self": 0.000496616000020822 }, "communicator.exchange": { "total": 0.057139930999994704, "count": 1, "is_parallel": true, "self": 0.057139930999994704 }, "steps_from_proto": { "total": 0.0017179459999852043, "count": 1, "is_parallel": true, "self": 0.00037093499992124634, "children": { "_process_rank_one_or_two_observation": { "total": 0.001347011000063958, "count": 8, "is_parallel": true, "self": 0.001347011000063958 } } } } } } }, "UnityEnvironment.step": { "total": 1154.8666738339514, "count": 63229, "is_parallel": true, "self": 35.45512123395997, "children": { "UnityEnvironment._generate_step_input": { "total": 24.310671551992755, "count": 63229, "is_parallel": true, "self": 24.310671551992755 }, "communicator.exchange": { "total": 996.5013080150507, "count": 63229, "is_parallel": true, "self": 996.5013080150507 }, "steps_from_proto": { "total": 98.599573032948, "count": 63229, "is_parallel": true, "self": 19.505024316975494, "children": { "_process_rank_one_or_two_observation": { "total": 79.09454871597251, "count": 505832, "is_parallel": true, "self": 79.09454871597251 } } } } } } } } } } }, "trainer_advance": { "total": 637.3957178369865, "count": 63230, "self": 2.6061248550181517, "children": { "process_trajectory": { "total": 125.45382269896936, "count": 63230, "self": 125.21713044296916, "children": { "RLTrainer._checkpoint": { "total": 0.23669225600019672, "count": 2, "self": 0.23669225600019672 } } }, "_update_policy": { "total": 509.33577028299896, "count": 443, "self": 302.5042601789859, "children": { "TorchPPOOptimizer.update": { "total": 206.8315101040131, "count": 22764, "self": 206.8315101040131 } } } } } } }, "trainer_threads": { "total": 1.2650002645386849e-06, "count": 1, "self": 1.2650002645386849e-06 }, "TrainerController._save_models": { "total": 0.11905292700021164, "count": 1, "self": 0.0020802680000997498, "children": { "RLTrainer._checkpoint": { "total": 0.11697265900011189, "count": 1, "self": 0.11697265900011189 } } } } } } }