{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.12530042231082916, "min": 0.11758170276880264, "max": 1.4623968601226807, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3795.09912109375, "min": 3544.3828125, "max": 44363.26953125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999935.0, "min": 29952.0, "max": 2999935.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999935.0, "min": 29952.0, "max": 2999935.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7794694900512695, "min": -0.12581132352352142, "max": 0.8871976137161255, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 233.06138610839844, "min": -30.57215118408203, "max": 269.70806884765625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013617660850286484, "min": -0.05305878072977066, "max": 0.38107696175575256, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.071680545806885, "min": -14.325870513916016, "max": 90.31523895263672, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06668864378296128, "min": 0.06332928630818009, "max": 0.07527718086370218, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.933641012961458, "min": 0.48843737269919657, "max": 1.0776327850859766, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015113021432472973, "min": 0.0003899888091238052, "max": 0.018621311025483357, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2115823000546216, "min": 0.004289876900361857, "max": 0.26069835435676697, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4063709598142915e-06, "min": 1.4063709598142915e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.968919343740008e-05, "min": 1.968919343740008e-05, "max": 0.004027250757583133, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10046875714285715, "min": 0.10046875714285715, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4065626, "min": 1.3962282666666668, "max": 2.842416866666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.682883857142878e-05, "min": 5.682883857142878e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0007956037400000029, "min": 0.0007956037400000029, "max": 0.13425744498, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009158189408481121, "min": 0.008886491879820824, "max": 0.5615325570106506, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12821465730667114, "min": 0.12441088259220123, "max": 3.930727958679199, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 233.84297520661158, "min": 202.21333333333334, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28295.0, "min": 15984.0, "max": 33385.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7496247829730847, "min": -1.0000000521540642, "max": 1.784449318051338, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 211.70459873974323, "min": -31.998801663517952, "max": 267.66739770770073, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7496247829730847, "min": -1.0000000521540642, "max": 1.784449318051338, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 211.70459873974323, "min": -31.998801663517952, "max": 267.66739770770073, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.022597352704966503, "min": 0.020750649035678057, "max": 11.320017603226006, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.734279677300947, "min": 2.734279677300947, "max": 181.1202816516161, "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": "1673611398", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673622172" }, "total": 10773.972994929001, "count": 1, "self": 0.7415345670015085, "children": { "run_training.setup": { "total": 0.14499570099997072, "count": 1, "self": 0.14499570099997072 }, "TrainerController.start_learning": { "total": 10773.086464660999, "count": 1, "self": 7.441989713466683, "children": { "TrainerController._reset_env": { "total": 4.440407903999585, "count": 1, "self": 4.440407903999585 }, "TrainerController.advance": { "total": 10761.080140587532, "count": 195464, "self": 6.910499891524523, "children": { "env_step": { "total": 7218.539935791099, "count": 195464, "self": 6813.396876323788, "children": { "SubprocessEnvManager._take_step": { "total": 400.39649747449675, "count": 195464, "self": 19.26538600265485, "children": { "TorchPolicy.evaluate": { "total": 381.1311114718419, "count": 187564, "self": 84.6899272079936, "children": { "TorchPolicy.sample_actions": { "total": 296.4411842638483, "count": 187564, "self": 296.4411842638483 } } } } }, "workers": { "total": 4.74656199281435, "count": 195464, "self": 0.0, "children": { "worker_root": { "total": 10753.83121954867, "count": 195464, "is_parallel": true, "self": 4427.332200703235, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029062350004096515, "count": 1, "is_parallel": true, "self": 0.0010541669998929137, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018520680005167378, "count": 8, "is_parallel": true, "self": 0.0018520680005167378 } } }, "UnityEnvironment.step": { "total": 0.06552483300038148, "count": 1, "is_parallel": true, "self": 0.0006672150011581834, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005307530000209226, "count": 1, "is_parallel": true, "self": 0.0005307530000209226 }, "communicator.exchange": { "total": 0.0622894769994673, "count": 1, "is_parallel": true, "self": 0.0622894769994673 }, "steps_from_proto": { "total": 0.002037387999735074, "count": 1, "is_parallel": true, "self": 0.0004959360003340407, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015414519994010334, "count": 8, "is_parallel": true, "self": 0.0015414519994010334 } } } } } } }, "UnityEnvironment.step": { "total": 6326.499018845436, "count": 195463, "is_parallel": true, "self": 128.74677668654658, "children": { "UnityEnvironment._generate_step_input": { "total": 78.80999634612635, "count": 195463, "is_parallel": true, "self": 78.80999634612635 }, "communicator.exchange": { "total": 5730.876744883976, "count": 195463, "is_parallel": true, "self": 5730.876744883976 }, "steps_from_proto": { "total": 388.0655009287866, "count": 195463, "is_parallel": true, "self": 97.15597599610737, "children": { "_process_rank_one_or_two_observation": { "total": 290.90952493267923, "count": 1563704, "is_parallel": true, "self": 290.90952493267923 } } } } } } } } } } }, "trainer_advance": { "total": 3535.629704904909, "count": 195464, "self": 14.978971290142908, "children": { "process_trajectory": { "total": 620.741367486773, "count": 195464, "self": 620.1138219647719, "children": { "RLTrainer._checkpoint": { "total": 0.6275455220011281, "count": 6, "self": 0.6275455220011281 } } }, "_update_policy": { "total": 2899.909366127993, "count": 1401, "self": 734.9283789987876, "children": { "TorchPPOOptimizer.update": { "total": 2164.9809871292055, "count": 68385, "self": 2164.9809871292055 } } } } } } }, "trainer_threads": { "total": 1.8060000002151355e-06, "count": 1, "self": 1.8060000002151355e-06 }, "TrainerController._save_models": { "total": 0.12392465000084485, "count": 1, "self": 0.0032138450023921905, "children": { "RLTrainer._checkpoint": { "total": 0.12071080499845266, "count": 1, "self": 0.12071080499845266 } } } } } } }