{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37172985076904297, "min": 0.34571102261543274, "max": 1.445479154586792, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11163.791015625, "min": 10387.9248046875, "max": 43850.0546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5813844799995422, "min": -0.0868256688117981, "max": 0.6140081286430359, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.4621124267578, "min": -20.924985885620117, "max": 172.53628540039062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05329661816358566, "min": 0.0032884569372981787, "max": 0.2829437851905823, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 14.709866523742676, "min": 0.9141910076141357, "max": 68.189453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06917745723343109, "min": 0.06392349422962634, "max": 0.07422677007214107, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9684844012680354, "min": 0.5195873905049875, "max": 1.0851523949554667, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01704817772791584, "min": 0.0006166050289238135, "max": 0.01704817772791584, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23867448819082177, "min": 0.006166050289238135, "max": 0.23867448819082177, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.606576035935715e-06, "min": 7.606576035935715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010649206450310001, "min": 0.00010649206450310001, "max": 0.0033831953722683, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253549285714288, "min": 0.10253549285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354969000000002, "min": 1.3886848, "max": 2.5277316999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026329573642857153, "min": 0.00026329573642857153, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036861403100000014, "min": 0.0036861403100000014, "max": 0.11280039683000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012313558720052242, "min": 0.012237989343702793, "max": 0.3796263039112091, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17238982021808624, "min": 0.17133185267448425, "max": 2.657384157180786, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 318.01075268817203, "min": 294.25773195876286, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29575.0, "min": 15984.0, "max": 33081.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6174558948284836, "min": -1.0000000521540642, "max": 1.7049081506473678, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.42339821904898, "min": -30.54200166463852, "max": 167.08099876344204, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6174558948284836, "min": -1.0000000521540642, "max": 1.7049081506473678, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.42339821904898, "min": -30.54200166463852, "max": 167.08099876344204, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04051789915957738, "min": 0.03948512167298016, "max": 7.186340016312897, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.768164621840697, "min": 3.768164621840697, "max": 114.98144026100636, "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": "1745286871", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1745289152" }, "total": 2281.8989853329995, "count": 1, "self": 0.8153226540007381, "children": { "run_training.setup": { "total": 0.030687765999573458, "count": 1, "self": 0.030687765999573458 }, "TrainerController.start_learning": { "total": 2281.052974912999, "count": 1, "self": 1.4093132709131169, "children": { "TrainerController._reset_env": { "total": 2.2530568610000046, "count": 1, "self": 2.2530568610000046 }, "TrainerController.advance": { "total": 2277.2669510440855, "count": 63825, "self": 1.4681138190344427, "children": { "env_step": { "total": 1571.9171799530714, "count": 63825, "self": 1415.0955414580567, "children": { "SubprocessEnvManager._take_step": { "total": 156.00860344499688, "count": 63825, "self": 4.753648962982879, "children": { "TorchPolicy.evaluate": { "total": 151.254954482014, "count": 62553, "self": 151.254954482014 } } }, "workers": { "total": 0.8130350500177883, "count": 63825, "self": 0.0, "children": { "worker_root": { "total": 2276.3098451840833, "count": 63825, "is_parallel": true, "self": 974.0282116371363, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022407769993151305, "count": 1, "is_parallel": true, "self": 0.0006508529995699064, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015899239997452241, "count": 8, "is_parallel": true, "self": 0.0015899239997452241 } } }, "UnityEnvironment.step": { "total": 0.0493720630001917, "count": 1, "is_parallel": true, "self": 0.0005702820008082199, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004829849995076074, "count": 1, "is_parallel": true, "self": 0.0004829849995076074 }, "communicator.exchange": { "total": 0.04672846900029981, "count": 1, "is_parallel": true, "self": 0.04672846900029981 }, "steps_from_proto": { "total": 0.0015903269995760638, "count": 1, "is_parallel": true, "self": 0.00032984299923555227, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012604840003405116, "count": 8, "is_parallel": true, "self": 0.0012604840003405116 } } } } } } }, "UnityEnvironment.step": { "total": 1302.281633546947, "count": 63824, "is_parallel": true, "self": 32.088897046703096, "children": { "UnityEnvironment._generate_step_input": { "total": 24.72722956511734, "count": 63824, "is_parallel": true, "self": 24.72722956511734 }, "communicator.exchange": { "total": 1147.8395586720371, "count": 63824, "is_parallel": true, "self": 1147.8395586720371 }, "steps_from_proto": { "total": 97.62594826308941, "count": 63824, "is_parallel": true, "self": 19.372896785787816, "children": { "_process_rank_one_or_two_observation": { "total": 78.2530514773016, "count": 510592, "is_parallel": true, "self": 78.2530514773016 } } } } } } } } } } }, "trainer_advance": { "total": 703.8816572719797, "count": 63825, "self": 2.6791413538348934, "children": { "process_trajectory": { "total": 128.41375720613632, "count": 63825, "self": 128.1723836701358, "children": { "RLTrainer._checkpoint": { "total": 0.24137353600053757, "count": 2, "self": 0.24137353600053757 } } }, "_update_policy": { "total": 572.7887587120085, "count": 449, "self": 318.1769304781383, "children": { "TorchPPOOptimizer.update": { "total": 254.61182823387026, "count": 22773, "self": 254.61182823387026 } } } } } } }, "trainer_threads": { "total": 1.1810006981249899e-06, "count": 1, "self": 1.1810006981249899e-06 }, "TrainerController._save_models": { "total": 0.12365255599979719, "count": 1, "self": 0.0015310060007323045, "children": { "RLTrainer._checkpoint": { "total": 0.12212154999906488, "count": 1, "self": 0.12212154999906488 } } } } } } }