{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.642172634601593, "min": 0.642172634601593, "max": 1.4805656671524048, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19131.607421875, "min": 19131.607421875, "max": 44914.44140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4079838991165161, "min": -0.26397669315338135, "max": 0.4315630793571472, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 107.70774841308594, "min": -62.562477111816406, "max": 116.95359802246094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.002595194848254323, "min": -0.2178112417459488, "max": 0.18550418317317963, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.6851314306259155, "min": -57.28435516357422, "max": 44.52100372314453, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0707030601063577, "min": 0.06505951898829412, "max": 0.07324577131629187, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9898428414890077, "min": 0.5127203992140431, "max": 1.0768232921174927, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013963222901067987, "min": 0.0002533068754298385, "max": 0.03407538086117901, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19548512061495182, "min": 0.003039682505158062, "max": 0.5111307129176852, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.654940305528572e-06, "min": 7.654940305528572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010716916427740001, "min": 0.00010716916427740001, "max": 0.003508013330662299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255161428571428, "min": 0.10255161428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357226, "min": 1.3886848, "max": 2.5693376999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026490626714285723, "min": 0.00026490626714285723, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037086877400000014, "min": 0.0037086877400000014, "max": 0.11695683622999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007136494852602482, "min": 0.007136494852602482, "max": 0.28169915080070496, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0999109297990799, "min": 0.0999109297990799, "max": 1.9718941450119019, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 488.9852941176471, "min": 410.81081081081084, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33251.0, "min": 15984.0, "max": 33424.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3344882145962293, "min": -1.0000000521540642, "max": 1.4545117438058643, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 90.7451985925436, "min": -30.999201618134975, "max": 107.35939835757017, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3344882145962293, "min": -1.0000000521540642, "max": 1.4545117438058643, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 90.7451985925436, "min": -30.999201618134975, "max": 107.35939835757017, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.036259704605874826, "min": 0.032090318124877136, "max": 5.475978604517877, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.465659913199488, "min": 2.1752223440125817, "max": 87.61565767228603, "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": "1759135832", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1759137895" }, "total": 2062.399851555, "count": 1, "self": 0.4303069309999046, "children": { "run_training.setup": { "total": 0.032243344999869805, "count": 1, "self": 0.032243344999869805 }, "TrainerController.start_learning": { "total": 2061.937301279, "count": 1, "self": 1.2171247989763287, "children": { "TrainerController._reset_env": { "total": 2.2456406619999143, "count": 1, "self": 2.2456406619999143 }, "TrainerController.advance": { "total": 2058.3983204150236, "count": 63548, "self": 1.2417737879759443, "children": { "env_step": { "total": 1422.2167690900278, "count": 63548, "self": 1283.0462695279657, "children": { "SubprocessEnvManager._take_step": { "total": 138.43949832503176, "count": 63548, "self": 4.291974304977657, "children": { "TorchPolicy.evaluate": { "total": 134.1475240200541, "count": 62552, "self": 134.1475240200541 } } }, "workers": { "total": 0.7310012370303411, "count": 63548, "self": 0.0, "children": { "worker_root": { "total": 2055.3477027509357, "count": 63548, "is_parallel": true, "self": 880.0893714509082, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017863380001017504, "count": 1, "is_parallel": true, "self": 0.000633719999996174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011526180001055764, "count": 8, "is_parallel": true, "self": 0.0011526180001055764 } } }, "UnityEnvironment.step": { "total": 0.048270240000192643, "count": 1, "is_parallel": true, "self": 0.0005147970002781221, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004455739999684738, "count": 1, "is_parallel": true, "self": 0.0004455739999684738 }, "communicator.exchange": { "total": 0.04571785500002079, "count": 1, "is_parallel": true, "self": 0.04571785500002079 }, "steps_from_proto": { "total": 0.001592013999925257, "count": 1, "is_parallel": true, "self": 0.00032465599997522077, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012673579999500362, "count": 8, "is_parallel": true, "self": 0.0012673579999500362 } } } } } } }, "UnityEnvironment.step": { "total": 1175.2583313000275, "count": 63547, "is_parallel": true, "self": 32.09587272102681, "children": { "UnityEnvironment._generate_step_input": { "total": 21.870403530016574, "count": 63547, "is_parallel": true, "self": 21.870403530016574 }, "communicator.exchange": { "total": 1021.2488769260347, "count": 63547, "is_parallel": true, "self": 1021.2488769260347 }, "steps_from_proto": { "total": 100.04317812294948, "count": 63547, "is_parallel": true, "self": 20.471825397034536, "children": { "_process_rank_one_or_two_observation": { "total": 79.57135272591495, "count": 508376, "is_parallel": true, "self": 79.57135272591495 } } } } } } } } } } }, "trainer_advance": { "total": 634.9397775370198, "count": 63548, "self": 2.4064408829867716, "children": { "process_trajectory": { "total": 118.0116583780316, "count": 63548, "self": 117.83537837103154, "children": { "RLTrainer._checkpoint": { "total": 0.1762800070000594, "count": 2, "self": 0.1762800070000594 } } }, "_update_policy": { "total": 514.5216782760015, "count": 446, "self": 285.92432495798926, "children": { "TorchPPOOptimizer.update": { "total": 228.5973533180122, "count": 22770, "self": 228.5973533180122 } } } } } } }, "trainer_threads": { "total": 9.350001164420974e-07, "count": 1, "self": 9.350001164420974e-07 }, "TrainerController._save_models": { "total": 0.07621446800021658, "count": 1, "self": 0.0011342440002408694, "children": { "RLTrainer._checkpoint": { "total": 0.07508022399997571, "count": 1, "self": 0.07508022399997571 } } } } } } }