{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1637401282787323, "min": 0.14609041810035706, "max": 1.4427152872085571, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4909.583984375, "min": 4368.52587890625, "max": 43766.2109375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999937.0, "min": 29952.0, "max": 2999937.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999937.0, "min": 29952.0, "max": 2999937.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.846611738204956, "min": -0.08420778810977936, "max": 0.8947031497955322, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 261.60302734375, "min": -20.378284454345703, "max": 274.6738586425781, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018006421625614166, "min": -0.03845600411295891, "max": 0.3556283712387085, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.563984394073486, "min": -10.267752647399902, "max": 85.70643615722656, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06976480790763162, "min": 0.0629069840558185, "max": 0.07433067837735595, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9767073107068427, "min": 0.4869086456742009, "max": 1.106910755841276, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016974806117581294, "min": 0.0012057348645284427, "max": 0.016974806117581294, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2376472856461381, "min": 0.015674553238869755, "max": 0.2376472856461381, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4569138001095244e-06, "min": 1.4569138001095244e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.039679320153334e-05, "min": 2.039679320153334e-05, "max": 0.0040727329424224, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048560476190475, "min": 0.10048560476190475, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067984666666666, "min": 1.3962282666666668, "max": 2.8575776000000004, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.851191571428573e-05, "min": 5.851191571428573e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008191668200000003, "min": 0.0008191668200000003, "max": 0.13577200224, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00963946245610714, "min": 0.009250648319721222, "max": 0.5485305190086365, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13495247066020966, "min": 0.1295090764760971, "max": 3.8397138118743896, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 206.07692307692307, "min": 194.02649006622516, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29469.0, "min": 15984.0, "max": 33176.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7939230698597182, "min": -1.0000000521540642, "max": 1.8052666609485943, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 256.5309989899397, "min": -27.89780167490244, "max": 270.78999914228916, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7939230698597182, "min": -1.0000000521540642, "max": 1.8052666609485943, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 256.5309989899397, "min": -27.89780167490244, "max": 270.78999914228916, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.020644184421455665, "min": 0.020644184421455665, "max": 9.808239279314876, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.95211837226816, "min": 2.842791608229163, "max": 156.931828469038, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708369934", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708377590" }, "total": 7655.921757800999, "count": 1, "self": 0.49041271599890024, "children": { "run_training.setup": { "total": 0.05162339000003158, "count": 1, "self": 0.05162339000003158 }, "TrainerController.start_learning": { "total": 7655.379721695001, "count": 1, "self": 4.679083708921098, "children": { "TrainerController._reset_env": { "total": 3.4450120569999854, "count": 1, "self": 3.4450120569999854 }, "TrainerController.advance": { "total": 7647.160700866079, "count": 195469, "self": 4.914604939637684, "children": { "env_step": { "total": 5698.804948522288, "count": 195469, "self": 5279.700916399172, "children": { "SubprocessEnvManager._take_step": { "total": 416.1765516500062, "count": 195469, "self": 15.121899494897889, "children": { "TorchPolicy.evaluate": { "total": 401.05465215510833, "count": 187566, "self": 401.05465215510833 } } }, "workers": { "total": 2.927480473110677, "count": 195469, "self": 0.0, "children": { "worker_root": { "total": 7637.867493341897, "count": 195469, "is_parallel": true, "self": 2736.80620130819, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005484271000000263, "count": 1, "is_parallel": true, "self": 0.004118847999848185, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013654230001520773, "count": 8, "is_parallel": true, "self": 0.0013654230001520773 } } }, "UnityEnvironment.step": { "total": 0.05068292399994334, "count": 1, "is_parallel": true, "self": 0.0006656719999682537, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000603673999989951, "count": 1, "is_parallel": true, "self": 0.000603673999989951 }, "communicator.exchange": { "total": 0.04775961899997583, "count": 1, "is_parallel": true, "self": 0.04775961899997583 }, "steps_from_proto": { "total": 0.0016539590000093085, "count": 1, "is_parallel": true, "self": 0.00034361600012289273, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013103429998864158, "count": 8, "is_parallel": true, "self": 0.0013103429998864158 } } } } } } }, "UnityEnvironment.step": { "total": 4901.061292033707, "count": 195468, "is_parallel": true, "self": 112.72846166643467, "children": { "UnityEnvironment._generate_step_input": { "total": 73.47705010319021, "count": 195468, "is_parallel": true, "self": 73.47705010319021 }, "communicator.exchange": { "total": 4404.901163487844, "count": 195468, "is_parallel": true, "self": 4404.901163487844 }, "steps_from_proto": { "total": 309.95461677623825, "count": 195468, "is_parallel": true, "self": 64.41757302254257, "children": { "_process_rank_one_or_two_observation": { "total": 245.53704375369568, "count": 1563744, "is_parallel": true, "self": 245.53704375369568 } } } } } } } } } } }, "trainer_advance": { "total": 1943.4411474041535, "count": 195469, "self": 9.994788128065238, "children": { "process_trajectory": { "total": 401.6005064070903, "count": 195469, "self": 401.03993008809016, "children": { "RLTrainer._checkpoint": { "total": 0.5605763190001198, "count": 6, "self": 0.5605763190001198 } } }, "_update_policy": { "total": 1531.845852868998, "count": 1401, "self": 902.8180489239654, "children": { "TorchPPOOptimizer.update": { "total": 629.0278039450326, "count": 68361, "self": 629.0278039450326 } } } } } } }, "trainer_threads": { "total": 1.0519997886149213e-06, "count": 1, "self": 1.0519997886149213e-06 }, "TrainerController._save_models": { "total": 0.09492401100033021, "count": 1, "self": 0.00147535599899129, "children": { "RLTrainer._checkpoint": { "total": 0.09344865500133892, "count": 1, "self": 0.09344865500133892 } } } } } } }