{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.25084295868873596, "min": 0.23805944621562958, "max": 1.4518606662750244, "count": 60 }, "Pyramids.Policy.Entropy.sum": { "value": 7493.18115234375, "min": 7145.74755859375, "max": 44043.64453125, "count": 60 }, "Pyramids.Step.mean": { "value": 1799938.0, "min": 29972.0, "max": 1799938.0, "count": 60 }, "Pyramids.Step.sum": { "value": 1799938.0, "min": 29972.0, "max": 1799938.0, "count": 60 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7553142309188843, "min": -0.08700596541166306, "max": 0.8099051117897034, "count": 60 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 220.5517578125, "min": -20.96843719482422, "max": 241.35171508789062, "count": 60 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005042566917836666, "min": -0.037025656551122665, "max": 0.25854551792144775, "count": 60 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.4724295139312744, "min": -10.256107330322266, "max": 61.53383255004883, "count": 60 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07158387741203316, "min": 0.06368594106881775, "max": 0.07468659836785538, "count": 60 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0737581611804974, "min": 0.4914486884841483, "max": 1.0737581611804974, "count": 60 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015331970093150932, "min": 0.0006989264041421586, "max": 0.017185425392947058, "count": 60 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22997955139726398, "min": 0.009086043253848063, "max": 0.2577813808942059, "count": 60 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00012151055282983555, "min": 0.00012151055282983555, "max": 0.0002984125148148762, "count": 60 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0018226582924475332, "min": 0.0017438468187180004, "max": 0.004027616657461167, "count": 60 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1405034977777778, "min": 0.1405034977777778, "max": 0.1994708380952381, "count": 60 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1075524666666667, "min": 1.3962958666666667, "max": 2.8425388333333332, "count": 60 }, "Pyramids.Policy.Beta.mean": { "value": 0.004056299428, "min": 0.004056299428, "max": 0.009947136725714286, "count": 60 }, "Pyramids.Policy.Beta.sum": { "value": 0.06084449142, "min": 0.058210071800000006, "max": 0.13426962945, "count": 60 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00800631195306778, "min": 0.007875305600464344, "max": 0.4587758183479309, "count": 60 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1200946792960167, "min": 0.11025427281856537, "max": 3.211430788040161, "count": 60 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 258.89565217391305, "min": 241.472, "max": 983.5806451612904, "count": 60 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29773.0, "min": 16643.0, "max": 33840.0, "count": 60 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6889182441908381, "min": -0.9198645651340485, "max": 1.7574094383735357, "count": 60 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 194.22559808194637, "min": -28.515801519155502, "max": 223.19099867343903, "count": 60 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6889182441908381, "min": -0.9198645651340485, "max": 1.7574094383735357, "count": 60 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 194.22559808194637, "min": -28.515801519155502, "max": 223.19099867343903, "count": 60 }, "Pyramids.Policy.RndReward.mean": { "value": 0.021789797905797097, "min": 0.020514660480895917, "max": 8.58361718935125, "count": 60 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5058267591666663, "min": 2.441244597226614, "max": 145.92149221897125, "count": 60 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1755411441", "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": "1755417020" }, "total": 5579.189633266, "count": 1, "self": 0.4671865020000041, "children": { "run_training.setup": { "total": 0.03165817500007506, "count": 1, "self": 0.03165817500007506 }, "TrainerController.start_learning": { "total": 5578.690788589, "count": 1, "self": 3.694829799186664, "children": { "TrainerController._reset_env": { "total": 2.640106629999991, "count": 1, "self": 2.640106629999991 }, "TrainerController.advance": { "total": 5572.243226584813, "count": 116352, "self": 3.7664057456877345, "children": { "env_step": { "total": 3818.466319450098, "count": 116352, "self": 3555.0399102949787, "children": { "SubprocessEnvManager._take_step": { "total": 261.13804135614646, "count": 116352, "self": 10.557156441956522, "children": { "TorchPolicy.evaluate": { "total": 250.58088491418994, "count": 112575, "self": 250.58088491418994 } } }, "workers": { "total": 2.288367798973013, "count": 116351, "self": 0.0, "children": { "worker_root": { "total": 5565.522609457939, "count": 116351, "is_parallel": true, "self": 2286.0096685508465, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002576033999957872, "count": 1, "is_parallel": true, "self": 0.0007288230001449847, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018472109998128872, "count": 8, "is_parallel": true, "self": 0.0018472109998128872 } } }, "UnityEnvironment.step": { "total": 0.0568356329999915, "count": 1, "is_parallel": true, "self": 0.0006172759997298272, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000551930000028733, "count": 1, "is_parallel": true, "self": 0.000551930000028733 }, "communicator.exchange": { "total": 0.05369985100014674, "count": 1, "is_parallel": true, "self": 0.05369985100014674 }, "steps_from_proto": { "total": 0.0019665760000862065, "count": 1, "is_parallel": true, "self": 0.0004393190001792391, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015272569999069674, "count": 8, "is_parallel": true, "self": 0.0015272569999069674 } } } } } } }, "UnityEnvironment.step": { "total": 3279.512940907093, "count": 116350, "is_parallel": true, "self": 73.71196718815418, "children": { "UnityEnvironment._generate_step_input": { "total": 51.55972680999389, "count": 116350, "is_parallel": true, "self": 51.55972680999389 }, "communicator.exchange": { "total": 2939.882080087019, "count": 116350, "is_parallel": true, "self": 2939.882080087019 }, "steps_from_proto": { "total": 214.359166821926, "count": 116350, "is_parallel": true, "self": 45.064863292046766, "children": { "_process_rank_one_or_two_observation": { "total": 169.29430352987924, "count": 930800, "is_parallel": true, "self": 169.29430352987924 } } } } } } } } } } }, "trainer_advance": { "total": 1750.0105013890272, "count": 116351, "self": 7.10484755782295, "children": { "process_trajectory": { "total": 266.94412531321063, "count": 116351, "self": 266.71287206521106, "children": { "RLTrainer._checkpoint": { "total": 0.23125324799957525, "count": 3, "self": 0.23125324799957525 } } }, "_update_policy": { "total": 1475.9615285179937, "count": 836, "self": 593.2146998489768, "children": { "TorchPPOOptimizer.update": { "total": 882.7468286690168, "count": 41025, "self": 882.7468286690168 } } } } } } }, "trainer_threads": { "total": 1.6089998098323122e-06, "count": 1, "self": 1.6089998098323122e-06 }, "TrainerController._save_models": { "total": 0.11262396599977365, "count": 1, "self": 0.002091240999106958, "children": { "RLTrainer._checkpoint": { "total": 0.11053272500066669, "count": 1, "self": 0.11053272500066669 } } } } } } }