{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.11522207409143448, "min": 0.11335458606481552, "max": 0.40282687544822693, "count": 67 }, "Pyramids.Policy.Entropy.sum": { "value": 3408.729736328125, "min": 3378.87353515625, "max": 12078.361328125, "count": 67 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 235.73170731707316, "min": 208.79710144927537, "max": 392.58024691358025, "count": 67 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28995.0, "min": 16229.0, "max": 31799.0, "count": 67 }, "Pyramids.Step.mean": { "value": 2999953.0, "min": 1019843.0, "max": 2999953.0, "count": 67 }, "Pyramids.Step.sum": { "value": 2999953.0, "min": 1019843.0, "max": 2999953.0, "count": 67 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7724880576133728, "min": 0.4972357749938965, "max": 0.8250284790992737, "count": 67 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 132.095458984375, "min": 56.92182540893555, "max": 155.04977416992188, "count": 67 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06514906883239746, "min": -0.0021130673121660948, "max": 0.13866503536701202, "count": 67 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.140490531921387, "min": -0.3782390356063843, "max": 21.909076690673828, "count": 67 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7646209549519323, "min": 1.4780292383781293, "max": 1.790804328477901, "count": 67 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 218.8129984140396, "min": 94.76899874210358, "max": 249.5273967385292, "count": 67 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7646209549519323, "min": 1.4780292383781293, "max": 1.790804328477901, "count": 67 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 218.8129984140396, "min": 94.76899874210358, "max": 249.5273967385292, "count": 67 }, "Pyramids.Policy.RndReward.mean": { "value": 0.12356506994899152, "min": 0.11194740364959031, "max": 0.31913066848476485, "count": 67 }, "Pyramids.Policy.RndReward.sum": { "value": 15.322068673674949, "min": 13.35549175227061, "max": 26.168714815750718, "count": 67 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.034386266389143806, "min": 0.030005244615798194, "max": 0.038253214486758225, "count": 67 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.13754506555657522, "min": 0.07650642897351645, "max": 0.15256832615705207, "count": 67 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013929035034379922, "min": 0.012917489361522408, "max": 0.0188918145140633, "count": 67 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.05571614013751969, "min": 0.0328423316241242, "max": 0.0688383637655837, "count": 67 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.3307495564499943e-06, "min": 1.3307495564499943e-06, "max": 0.00019873528375491669, "count": 67 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.322998225799977e-06, "min": 5.322998225799977e-06, "max": 0.0007748959417014, "count": 67 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10044355, "min": 0.10044355, "max": 0.16624508333333332, "count": 67 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.4017742, "min": 0.30751126666666667, "max": 0.6582986, "count": 67 }, "Pyramids.Policy.Beta.mean": { "value": 5.431064499999981e-05, "min": 5.431064499999981e-05, "max": 0.006627883825, "count": 67 }, "Pyramids.Policy.Beta.sum": { "value": 0.00021724257999999923, "min": 0.00021724257999999923, "max": 0.025844030139999998, "count": 67 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02532372996211052, "min": 0.02520296908915043, "max": 0.06924465298652649, "count": 67 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10129491984844208, "min": 0.07792649418115616, "max": 0.15872585773468018, "count": 67 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1751022273", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/mtn/miniconda3/envs/mlagents310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --torch-device=cuda --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1751027194" }, "total": 4589.448268449003, "count": 1, "self": 0.3217653830033669, "children": { "run_training.setup": { "total": 0.023277966000023298, "count": 1, "self": 0.023277966000023298 }, "TrainerController.start_learning": { "total": 4589.1032251, "count": 1, "self": 3.189808445989911, "children": { "TrainerController._reset_env": { "total": 2.2403230070012796, "count": 1, "self": 2.2403230070012796 }, "TrainerController.advance": { "total": 4583.137820398009, "count": 131038, "self": 3.095331170632562, "children": { "env_step": { "total": 3616.747075870615, "count": 131038, "self": 2935.1100005209482, "children": { "SubprocessEnvManager._take_step": { "total": 679.5315629338038, "count": 131038, "self": 10.55458963710771, "children": { "TorchPolicy.evaluate": { "total": 668.9769732966961, "count": 125070, "self": 668.9769732966961 } } }, "workers": { "total": 2.105512415862904, "count": 131038, "self": 0.0, "children": { "worker_root": { "total": 4581.505453005251, "count": 131038, "is_parallel": true, "self": 1857.6158370692538, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017467950019636191, "count": 1, "is_parallel": true, "self": 0.0006292129983194172, "children": { "_process_rank_one_or_two_observation": { "total": 0.001117582003644202, "count": 8, "is_parallel": true, "self": 0.001117582003644202 } } }, "UnityEnvironment.step": { "total": 0.03971043199999258, "count": 1, "is_parallel": true, "self": 0.000289715997496387, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002698230018722825, "count": 1, "is_parallel": true, "self": 0.0002698230018722825 }, "communicator.exchange": { "total": 0.038202450999961, "count": 1, "is_parallel": true, "self": 0.038202450999961 }, "steps_from_proto": { "total": 0.000948442000662908, "count": 1, "is_parallel": true, "self": 0.00025254400316043757, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006958979975024704, "count": 8, "is_parallel": true, "self": 0.0006958979975024704 } } } } } } }, "UnityEnvironment.step": { "total": 2723.8896159359974, "count": 131037, "is_parallel": true, "self": 37.66285123646958, "children": { "UnityEnvironment._generate_step_input": { "total": 26.991314424940356, "count": 131037, "is_parallel": true, "self": 26.991314424940356 }, "communicator.exchange": { "total": 2563.454466873187, "count": 131037, "is_parallel": true, "self": 2563.454466873187 }, "steps_from_proto": { "total": 95.78098340140059, "count": 131037, "is_parallel": true, "self": 21.66337494808249, "children": { "_process_rank_one_or_two_observation": { "total": 74.1176084533181, "count": 1048296, "is_parallel": true, "self": 74.1176084533181 } } } } } } } } } } }, "trainer_advance": { "total": 963.2954133567619, "count": 131038, "self": 7.05218511345447, "children": { "process_trajectory": { "total": 262.79297143431904, "count": 131038, "self": 260.70810050631553, "children": { "RLTrainer._checkpoint": { "total": 2.084870928003511, "count": 4, "self": 2.084870928003511 } } }, "_update_policy": { "total": 693.4502568089883, "count": 241, "self": 404.0553244968396, "children": { "TorchPPOOptimizer.update": { "total": 289.39493231214874, "count": 11568, "self": 289.39493231214874 } } } } } } }, "trainer_threads": { "total": 7.369999366346747e-07, "count": 1, "self": 7.369999366346747e-07 }, "TrainerController._save_models": { "total": 0.5352725119992101, "count": 1, "self": 0.028642640998441493, "children": { "RLTrainer._checkpoint": { "total": 0.5066298710007686, "count": 1, "self": 0.5066298710007686 } } } } } } }