{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.433766633272171, "min": 0.4125324785709381, "max": 1.3705247640609741, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13068.521484375, "min": 12358.302734375, "max": 41576.23828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44390353560447693, "min": -0.19857318699359894, "max": 0.44390353560447693, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 118.07833862304688, "min": -47.06184387207031, "max": 119.3135986328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.17124733328819275, "min": -0.0018331421306356788, "max": 0.2085869163274765, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 45.55179214477539, "min": -0.4949483871459961, "max": 50.06085968017578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07033163314779466, "min": 0.06453366591577993, "max": 0.0756166204012087, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9846428640691253, "min": 0.4977563099427839, "max": 1.047348028436924, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017073303731324683, "min": 0.0006396095459644188, "max": 0.017073303731324683, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23902625223854557, "min": 0.006077761252030561, "max": 0.23902625223854557, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4205975264999945e-06, "min": 7.4205975264999945e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010388836537099993, "min": 0.00010388836537099993, "max": 0.0033823733725423, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247350000000001, "min": 0.10247350000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346290000000002, "min": 1.3691136000000002, "max": 2.5274577000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002571026499999999, "min": 0.0002571026499999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035994370999999983, "min": 0.0035994370999999983, "max": 0.11277302422999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010317884385585785, "min": 0.009919874370098114, "max": 0.4398839771747589, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.144450381398201, "min": 0.1388782411813736, "max": 3.0791878700256348, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 419.42028985507244, "min": 414.90909090909093, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28940.0, "min": 15984.0, "max": 32904.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3776144690919614, "min": -1.0000000521540642, "max": 1.4059971155864852, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 95.05539836734533, "min": -32.000001668930054, "max": 98.41979809105396, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3776144690919614, "min": -1.0000000521540642, "max": 1.4059971155864852, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 95.05539836734533, "min": -32.000001668930054, "max": 98.41979809105396, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043847105257884614, "min": 0.043847105257884614, "max": 8.086290083825588, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0254502627940383, "min": 3.0254502627940383, "max": 129.3806413412094, "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": "1700125918", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700128126" }, "total": 2208.0681602289997, "count": 1, "self": 0.8374318349997338, "children": { "run_training.setup": { "total": 0.043693949000044086, "count": 1, "self": 0.043693949000044086 }, "TrainerController.start_learning": { "total": 2207.187034445, "count": 1, "self": 1.301595414102394, "children": { "TrainerController._reset_env": { "total": 4.437943987999915, "count": 1, "self": 4.437943987999915 }, "TrainerController.advance": { "total": 2201.369786762898, "count": 63586, "self": 1.3813469129836449, "children": { "env_step": { "total": 1558.023678903949, "count": 63586, "self": 1427.6574466989382, "children": { "SubprocessEnvManager._take_step": { "total": 129.5405791349226, "count": 63586, "self": 4.601007559114805, "children": { "TorchPolicy.evaluate": { "total": 124.9395715758078, "count": 62565, "self": 124.9395715758078 } } }, "workers": { "total": 0.8256530700882649, "count": 63586, "self": 0.0, "children": { "worker_root": { "total": 2202.4467842660606, "count": 63586, "is_parallel": true, "self": 890.0110226921183, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018297380001968122, "count": 1, "is_parallel": true, "self": 0.000616780999735056, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012129570004617563, "count": 8, "is_parallel": true, "self": 0.0012129570004617563 } } }, "UnityEnvironment.step": { "total": 0.08557135199998811, "count": 1, "is_parallel": true, "self": 0.00057027000002563, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004818279999199149, "count": 1, "is_parallel": true, "self": 0.0004818279999199149 }, "communicator.exchange": { "total": 0.08281192399999782, "count": 1, "is_parallel": true, "self": 0.08281192399999782 }, "steps_from_proto": { "total": 0.0017073300000447489, "count": 1, "is_parallel": true, "self": 0.00038541799904123764, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013219120010035113, "count": 8, "is_parallel": true, "self": 0.0013219120010035113 } } } } } } }, "UnityEnvironment.step": { "total": 1312.4357615739423, "count": 63585, "is_parallel": true, "self": 34.12867691802285, "children": { "UnityEnvironment._generate_step_input": { "total": 23.095019455966394, "count": 63585, "is_parallel": true, "self": 23.095019455966394 }, "communicator.exchange": { "total": 1158.6799971030982, "count": 63585, "is_parallel": true, "self": 1158.6799971030982 }, "steps_from_proto": { "total": 96.5320680968548, "count": 63585, "is_parallel": true, "self": 19.111251783700936, "children": { "_process_rank_one_or_two_observation": { "total": 77.42081631315386, "count": 508680, "is_parallel": true, "self": 77.42081631315386 } } } } } } } } } } }, "trainer_advance": { "total": 641.9647609459653, "count": 63586, "self": 2.4968807479158386, "children": { "process_trajectory": { "total": 119.31303743905528, "count": 63586, "self": 119.1586252110551, "children": { "RLTrainer._checkpoint": { "total": 0.15441222800018295, "count": 2, "self": 0.15441222800018295 } } }, "_update_policy": { "total": 520.1548427589942, "count": 441, "self": 315.4202880491198, "children": { "TorchPPOOptimizer.update": { "total": 204.73455470987437, "count": 22860, "self": 204.73455470987437 } } } } } } }, "trainer_threads": { "total": 1.032999534800183e-06, "count": 1, "self": 1.032999534800183e-06 }, "TrainerController._save_models": { "total": 0.07770724700003484, "count": 1, "self": 0.0013933420004832442, "children": { "RLTrainer._checkpoint": { "total": 0.0763139049995516, "count": 1, "self": 0.0763139049995516 } } } } } } }