{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48553845286369324, "min": 0.48177430033683777, "max": 1.5041900873184204, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14480.69921875, "min": 14480.69921875, "max": 45631.109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989937.0, "min": 29952.0, "max": 989937.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989937.0, "min": 29952.0, "max": 989937.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4714486300945282, "min": -0.11293534934520721, "max": 0.5205168128013611, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.1769256591797, "min": -27.10448455810547, "max": 141.58056640625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.7862393856048584, "min": -0.7862393856048584, "max": 1.7319328784942627, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -215.42959594726562, "min": -215.42959594726562, "max": 471.08575439453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06264005121691275, "min": 0.06264005121691275, "max": 0.0731694215884943, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9396007682536912, "min": 0.47806689984716433, "max": 1.0450212277389843, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.11705784040093849, "min": 0.00027009772500621003, "max": 0.3335242840777418, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.7558676060140772, "min": 0.0021607818000496802, "max": 4.669339977088385, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.453257515613336e-06, "min": 7.453257515613336e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011179886273420004, "min": 0.00011179886273420004, "max": 0.0032530037156654995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248438666666666, "min": 0.10248438666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372658, "min": 1.327104, "max": 2.4431376, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025819022800000017, "min": 0.00025819022800000017, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038728534200000025, "min": 0.0038728534200000025, "max": 0.10845501655, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008008955977857113, "min": 0.008008955977857113, "max": 0.27402421832084656, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12013433873653412, "min": 0.11584556102752686, "max": 1.918169617652893, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 397.1449275362319, "min": 364.2151898734177, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27403.0, "min": 15984.0, "max": 32908.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5158840409223584, "min": -1.0000000521540642, "max": 1.5344860553741455, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.59599882364273, "min": -32.000001668930054, "max": 122.13759824633598, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5158840409223584, "min": -1.0000000521540642, "max": 1.5344860553741455, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.59599882364273, "min": -32.000001668930054, "max": 122.13759824633598, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.032990601458299934, "min": 0.0311697374914568, "max": 5.301625814288855, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2763515006226953, "min": 2.2763515006226953, "max": 84.82601302862167, "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": "1722592918", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722595032" }, "total": 2113.667739869, "count": 1, "self": 0.47670927299895993, "children": { "run_training.setup": { "total": 0.05849010900055873, "count": 1, "self": 0.05849010900055873 }, "TrainerController.start_learning": { "total": 2113.1325404870004, "count": 1, "self": 1.6507412319906507, "children": { "TrainerController._reset_env": { "total": 1.8085409149998668, "count": 1, "self": 1.8085409149998668 }, "TrainerController.advance": { "total": 2109.5753017550087, "count": 63584, "self": 1.3952505010147433, "children": { "env_step": { "total": 1477.7651334989314, "count": 63584, "self": 1344.9789136409563, "children": { "SubprocessEnvManager._take_step": { "total": 131.96149753799818, "count": 63584, "self": 4.677737312900717, "children": { "TorchPolicy.evaluate": { "total": 127.28376022509747, "count": 62566, "self": 127.28376022509747 } } }, "workers": { "total": 0.8247223199768996, "count": 63584, "self": 0.0, "children": { "worker_root": { "total": 2107.940580559017, "count": 63584, "is_parallel": true, "self": 883.2607354790653, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002009505999922112, "count": 1, "is_parallel": true, "self": 0.0006411679996745079, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013683380002476042, "count": 8, "is_parallel": true, "self": 0.0013683380002476042 } } }, "UnityEnvironment.step": { "total": 0.051794814000459155, "count": 1, "is_parallel": true, "self": 0.0006312819996310282, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046004200066818157, "count": 1, "is_parallel": true, "self": 0.00046004200066818157 }, "communicator.exchange": { "total": 0.049080130999755056, "count": 1, "is_parallel": true, "self": 0.049080130999755056 }, "steps_from_proto": { "total": 0.0016233590004048892, "count": 1, "is_parallel": true, "self": 0.00035576100071921246, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012675979996856768, "count": 8, "is_parallel": true, "self": 0.0012675979996856768 } } } } } } }, "UnityEnvironment.step": { "total": 1224.6798450799515, "count": 63583, "is_parallel": true, "self": 33.40432016192335, "children": { "UnityEnvironment._generate_step_input": { "total": 23.274641733985845, "count": 63583, "is_parallel": true, "self": 23.274641733985845 }, "communicator.exchange": { "total": 1068.8719454249613, "count": 63583, "is_parallel": true, "self": 1068.8719454249613 }, "steps_from_proto": { "total": 99.12893775908105, "count": 63583, "is_parallel": true, "self": 20.086342773817705, "children": { "_process_rank_one_or_two_observation": { "total": 79.04259498526335, "count": 508664, "is_parallel": true, "self": 79.04259498526335 } } } } } } } } } } }, "trainer_advance": { "total": 630.4149177550626, "count": 63584, "self": 2.53545622305046, "children": { "process_trajectory": { "total": 129.731635275004, "count": 63584, "self": 129.53490644900467, "children": { "RLTrainer._checkpoint": { "total": 0.19672882599934383, "count": 2, "self": 0.19672882599934383 } } }, "_update_policy": { "total": 498.1478262570081, "count": 436, "self": 296.10360297507214, "children": { "TorchPPOOptimizer.update": { "total": 202.04422328193596, "count": 22794, "self": 202.04422328193596 } } } } } } }, "trainer_threads": { "total": 9.120003596763127e-07, "count": 1, "self": 9.120003596763127e-07 }, "TrainerController._save_models": { "total": 0.0979556730007971, "count": 1, "self": 0.0014483460008705151, "children": { "RLTrainer._checkpoint": { "total": 0.09650732699992659, "count": 1, "self": 0.09650732699992659 } } } } } } }