{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5914092659950256, "min": 0.5893111228942871, "max": 1.4677213430404663, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17761.203125, "min": 17537.8984375, "max": 44524.79296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1261201947927475, "min": -0.34923824667930603, "max": 0.21711064875125885, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 31.530048370361328, "min": -82.76946258544922, "max": 55.14610290527344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025204800069332123, "min": -0.001280400319956243, "max": 0.43257439136505127, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.301199913024902, "min": -0.32138046622276306, "max": 102.52013397216797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06728591255128336, "min": 0.06556427793069802, "max": 0.07352719386579468, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.942002775717967, "min": 0.5008840780901247, "max": 1.0190106177789287, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007789448115443195, "min": 0.00010343481080217545, "max": 0.010216503568494809, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10905227361620473, "min": 0.0014480873512304564, "max": 0.117371979493827, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.66344744555e-06, "min": 7.66344744555e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001072882642377, "min": 0.0001072882642377, "max": 0.0032604002131999994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255444999999999, "min": 0.10255444999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357623, "min": 1.3886848, "max": 2.3868, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002651895550000001, "min": 0.0002651895550000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003712653770000001, "min": 0.003712653770000001, "max": 0.10870132, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01552666537463665, "min": 0.01552666537463665, "max": 0.5615646243095398, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2173733115196228, "min": 0.2173733115196228, "max": 3.930952548980713, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 673.1463414634146, "min": 673.1463414634146, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27599.0, "min": 15984.0, "max": 33431.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6437072822960411, "min": -1.0000000521540642, "max": 0.8264633853261064, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 26.391998574137688, "min": -31.99920167028904, "max": 33.88499879837036, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6437072822960411, "min": -1.0000000521540642, "max": 0.8264633853261064, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 26.391998574137688, "min": -31.99920167028904, "max": 33.88499879837036, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10906141107652063, "min": 0.10906141107652063, "max": 11.398194424808025, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.471517854137346, "min": 4.471517854137346, "max": 182.3711107969284, "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": "1718186408", "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 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718188608" }, "total": 2200.465742006, "count": 1, "self": 0.647527412999807, "children": { "run_training.setup": { "total": 0.054914188000054764, "count": 1, "self": 0.054914188000054764 }, "TrainerController.start_learning": { "total": 2199.763300405, "count": 1, "self": 1.4302349780623445, "children": { "TrainerController._reset_env": { "total": 3.10037201800003, "count": 1, "self": 3.10037201800003 }, "TrainerController.advance": { "total": 2195.1437982349375, "count": 63241, "self": 1.456162030966425, "children": { "env_step": { "total": 1558.736653119969, "count": 63241, "self": 1420.6301927249629, "children": { "SubprocessEnvManager._take_step": { "total": 137.23265283699476, "count": 63241, "self": 4.8166962530012825, "children": { "TorchPolicy.evaluate": { "total": 132.41595658399348, "count": 62564, "self": 132.41595658399348 } } }, "workers": { "total": 0.8738075580113787, "count": 63241, "self": 0.0, "children": { "worker_root": { "total": 2194.40116029797, "count": 63241, "is_parallel": true, "self": 900.9212492189581, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009752143000014257, "count": 1, "is_parallel": true, "self": 0.008254776999990554, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014973660000237032, "count": 8, "is_parallel": true, "self": 0.0014973660000237032 } } }, "UnityEnvironment.step": { "total": 0.05192776799998455, "count": 1, "is_parallel": true, "self": 0.0008202449999998862, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000526607999972839, "count": 1, "is_parallel": true, "self": 0.000526607999972839 }, "communicator.exchange": { "total": 0.048833838999996715, "count": 1, "is_parallel": true, "self": 0.048833838999996715 }, "steps_from_proto": { "total": 0.001747076000015113, "count": 1, "is_parallel": true, "self": 0.0003702979998934097, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013767780001217034, "count": 8, "is_parallel": true, "self": 0.0013767780001217034 } } } } } } }, "UnityEnvironment.step": { "total": 1293.4799110790118, "count": 63240, "is_parallel": true, "self": 34.564377788030015, "children": { "UnityEnvironment._generate_step_input": { "total": 24.592697890988063, "count": 63240, "is_parallel": true, "self": 24.592697890988063 }, "communicator.exchange": { "total": 1131.231110088946, "count": 63240, "is_parallel": true, "self": 1131.231110088946 }, "steps_from_proto": { "total": 103.09172531104753, "count": 63240, "is_parallel": true, "self": 21.417419034972568, "children": { "_process_rank_one_or_two_observation": { "total": 81.67430627607496, "count": 505920, "is_parallel": true, "self": 81.67430627607496 } } } } } } } } } } }, "trainer_advance": { "total": 634.9509830840022, "count": 63241, "self": 2.550630025964324, "children": { "process_trajectory": { "total": 130.80887365003616, "count": 63241, "self": 130.5409999890361, "children": { "RLTrainer._checkpoint": { "total": 0.26787366100006693, "count": 2, "self": 0.26787366100006693 } } }, "_update_policy": { "total": 501.59147940800176, "count": 440, "self": 297.27792810998926, "children": { "TorchPPOOptimizer.update": { "total": 204.3135512980125, "count": 22776, "self": 204.3135512980125 } } } } } } }, "trainer_threads": { "total": 9.66999778029276e-07, "count": 1, "self": 9.66999778029276e-07 }, "TrainerController._save_models": { "total": 0.08889420700006667, "count": 1, "self": 0.0013217339997027011, "children": { "RLTrainer._checkpoint": { "total": 0.08757247300036397, "count": 1, "self": 0.08757247300036397 } } } } } } }