{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4942750930786133, "min": 0.48845791816711426, "max": 1.5298830270767212, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14551.458984375, "min": 14551.458984375, "max": 46410.53125, "count": 33 }, "Pyramids.Step.mean": { "value": 989938.0, "min": 29952.0, "max": 989938.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989938.0, "min": 29952.0, "max": 989938.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.30286291241645813, "min": -0.10219455510377884, "max": 0.3196588158607483, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 78.44149780273438, "min": -24.628887176513672, "max": 84.38993072509766, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022502778097987175, "min": 0.01734801195561886, "max": 0.7575384974479675, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.828219413757324, "min": 4.475787162780762, "max": 182.5667724609375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.049329291329098246, "min": 0.04611922146148506, "max": 0.055694993015971375, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.24664645664549123, "min": 0.20733615012270293, "max": 0.3183257812711721, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011204519529516498, "min": 0.0003459387007436525, "max": 0.03006256755965884, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.05602259764758249, "min": 0.0017296935037182627, "max": 0.12025027023863535, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2718297456359991e-05, "min": 1.2718297456359991e-05, "max": 0.0004924160015168, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 6.359148728179996e-05, "min": 6.359148728179996e-05, "max": 0.0026851160629768, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254364, "min": 0.10254364, "max": 0.1984832, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5127182, "min": 0.5127182, "max": 1.1370232000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026410963599999985, "min": 0.00026410963599999985, "max": 0.00984847168, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0013205481799999992, "min": 0.0013205481799999992, "max": 0.053708617679999994, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02056790702044964, "min": 0.02056790702044964, "max": 1.1150782108306885, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10283953696489334, "min": 0.10283953696489334, "max": 4.460312843322754, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 566.2727272727273, "min": 508.72727272727275, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31145.0, "min": 15984.0, "max": 33966.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9577444165393159, "min": -1.0000000521540642, "max": 1.2163153570145369, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 51.718198493123055, "min": -30.999001622200012, "max": 70.17759846150875, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9577444165393159, "min": -1.0000000521540642, "max": 1.2163153570145369, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 51.718198493123055, "min": -30.999001622200012, "max": 70.17759846150875, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11884490022418538, "min": 0.10795965244947833, "max": 17.38372228294611, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.41762461210601, "min": 6.045740537170786, "max": 278.13955652713776, "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": "1682640841", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", "command_line_arguments": "/home/qromaiko/mambaforge/envs/pytorch_rl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0", "numpy_version": "1.21.2", "end_time_seconds": "1682641966" }, "total": 1125.5063138549995, "count": 1, "self": 0.21812442599912174, "children": { "run_training.setup": { "total": 0.010721849001129158, "count": 1, "self": 0.010721849001129158 }, "TrainerController.start_learning": { "total": 1125.2774675799992, "count": 1, "self": 0.8694721743631817, "children": { "TrainerController._reset_env": { "total": 1.6154667800001334, "count": 1, "self": 1.6154667800001334 }, "TrainerController.advance": { "total": 1122.7409619466343, "count": 63428, "self": 0.7306516658172768, "children": { "env_step": { "total": 781.7817073699734, "count": 63428, "self": 670.7195662406557, "children": { "SubprocessEnvManager._take_step": { "total": 110.56133297691485, "count": 63428, "self": 2.4412032318177808, "children": { "TorchPolicy.evaluate": { "total": 108.12012974509707, "count": 62549, "self": 108.12012974509707 } } }, "workers": { "total": 0.5008081524028967, "count": 63428, "self": 0.0, "children": { "worker_root": { "total": 1123.2388217810003, "count": 63428, "is_parallel": true, "self": 506.3967249876587, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011530400006449781, "count": 1, "is_parallel": true, "self": 0.00034442999822204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008086100024229381, "count": 8, "is_parallel": true, "self": 0.0008086100024229381 } } }, "UnityEnvironment.step": { "total": 0.023295652001252165, "count": 1, "is_parallel": true, "self": 0.00023395999960484914, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002823799986799713, "count": 1, "is_parallel": true, "self": 0.0002823799986799713 }, "communicator.exchange": { "total": 0.022174442001414718, "count": 1, "is_parallel": true, "self": 0.022174442001414718 }, "steps_from_proto": { "total": 0.0006048700015526265, "count": 1, "is_parallel": true, "self": 0.0001431600067007821, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004617099948518444, "count": 8, "is_parallel": true, "self": 0.0004617099948518444 } } } } } } }, "UnityEnvironment.step": { "total": 616.8420967933416, "count": 63427, "is_parallel": true, "self": 12.591666257889301, "children": { "UnityEnvironment._generate_step_input": { "total": 8.881313343546935, "count": 63427, "is_parallel": true, "self": 8.881313343546935 }, "communicator.exchange": { "total": 560.5799187692137, "count": 63427, "is_parallel": true, "self": 560.5799187692137 }, "steps_from_proto": { "total": 34.7891984226917, "count": 63427, "is_parallel": true, "self": 7.904953766912513, "children": { "_process_rank_one_or_two_observation": { "total": 26.884244655779185, "count": 507416, "is_parallel": true, "self": 26.884244655779185 } } } } } } } } } } }, "trainer_advance": { "total": 340.2286029108436, "count": 63428, "self": 1.3467025126883527, "children": { "process_trajectory": { "total": 72.08541986214186, "count": 63428, "self": 71.96878907913924, "children": { "RLTrainer._checkpoint": { "total": 0.11663078300261986, "count": 2, "self": 0.11663078300261986 } } }, "_update_policy": { "total": 266.7964805360134, "count": 186, "self": 162.63030635508403, "children": { "TorchPPOOptimizer.update": { "total": 104.16617418092937, "count": 11496, "self": 104.16617418092937 } } } } } } }, "trainer_threads": { "total": 6.100017344579101e-07, "count": 1, "self": 6.100017344579101e-07 }, "TrainerController._save_models": { "total": 0.051566068999818526, "count": 1, "self": 0.0014411789998121094, "children": { "RLTrainer._checkpoint": { "total": 0.05012489000000642, "count": 1, "self": 0.05012489000000642 } } } } } } }