{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42644765973091125, "min": 0.42644765973091125, "max": 1.4192005395889282, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13018.59375, "min": 13018.59375, "max": 43052.8671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.08939199894666672, "min": -0.09554418921470642, "max": 0.11986298859119415, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 22.16921615600586, "min": -23.02614974975586, "max": 29.965747833251953, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.021285749971866608, "min": 0.01697336509823799, "max": 0.5067555904388428, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.278865814208984, "min": 4.192420959472656, "max": 120.10107421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06471121254467885, "min": 0.0643343778640709, "max": 0.07411832143049855, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9059569756255038, "min": 0.48206214528047775, "max": 1.0316440131316673, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007708617260229838, "min": 0.00014863693019116412, "max": 0.009413097717712666, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10792064164321773, "min": 0.001337732371720477, "max": 0.1359068791839758, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5364832021571445e-06, "min": 7.5364832021571445e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010551076483020003, "min": 0.00010551076483020003, "max": 0.0030006840997721003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251212857142859, "min": 0.10251212857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351698000000004, "min": 1.327104, "max": 2.4002279, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026096164428571434, "min": 0.00026096164428571434, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003653463020000001, "min": 0.003653463020000001, "max": 0.10006276721000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014164185151457787, "min": 0.014164185151457787, "max": 0.5066842436790466, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1982985883951187, "min": 0.1982985883951187, "max": 3.5467896461486816, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 780.8461538461538, "min": 708.65, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30453.0, "min": 15984.0, "max": 33253.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.3983794437387051, "min": -1.0000000521540642, "max": 0.6586053681534689, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 15.536798305809498, "min": -32.000001668930054, "max": 24.647798277437687, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.3983794437387051, "min": -1.0000000521540642, "max": 0.6586053681534689, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 15.536798305809498, "min": -32.000001668930054, "max": 24.647798277437687, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11415909783532605, "min": 0.11415909783532605, "max": 10.265303822234273, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.452204815577716, "min": 4.406150224851444, "max": 164.24486115574837, "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": "1698702470", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698704667" }, "total": 2197.196335996, "count": 1, "self": 0.48917991100006475, "children": { "run_training.setup": { "total": 0.04742555999999354, "count": 1, "self": 0.04742555999999354 }, "TrainerController.start_learning": { "total": 2196.6597305249998, "count": 1, "self": 1.429298409006151, "children": { "TrainerController._reset_env": { "total": 8.346174356999995, "count": 1, "self": 8.346174356999995 }, "TrainerController.advance": { "total": 2186.8062697699934, "count": 63215, "self": 1.491608549016746, "children": { "env_step": { "total": 1552.2577063800034, "count": 63215, "self": 1410.3793536139829, "children": { "SubprocessEnvManager._take_step": { "total": 140.98201270001903, "count": 63215, "self": 4.76855002804129, "children": { "TorchPolicy.evaluate": { "total": 136.21346267197774, "count": 62575, "self": 136.21346267197774 } } }, "workers": { "total": 0.896340066001386, "count": 63215, "self": 0.0, "children": { "worker_root": { "total": 2191.759337354998, "count": 63215, "is_parallel": true, "self": 904.1406981859702, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005038589000008642, "count": 1, "is_parallel": true, "self": 0.0036422089999916807, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013963800000169613, "count": 8, "is_parallel": true, "self": 0.0013963800000169613 } } }, "UnityEnvironment.step": { "total": 0.05343678999997792, "count": 1, "is_parallel": true, "self": 0.0006070340000121632, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000502630999989151, "count": 1, "is_parallel": true, "self": 0.000502630999989151 }, "communicator.exchange": { "total": 0.050540202999997064, "count": 1, "is_parallel": true, "self": 0.050540202999997064 }, "steps_from_proto": { "total": 0.0017869219999795405, "count": 1, "is_parallel": true, "self": 0.00040560899995512045, "children": { "_process_rank_one_or_two_observation": { "total": 0.00138131300002442, "count": 8, "is_parallel": true, "self": 0.00138131300002442 } } } } } } }, "UnityEnvironment.step": { "total": 1287.6186391690278, "count": 63214, "is_parallel": true, "self": 35.566995317031115, "children": { "UnityEnvironment._generate_step_input": { "total": 26.21681346901866, "count": 63214, "is_parallel": true, "self": 26.21681346901866 }, "communicator.exchange": { "total": 1121.3449699729445, "count": 63214, "is_parallel": true, "self": 1121.3449699729445 }, "steps_from_proto": { "total": 104.48986041003349, "count": 63214, "is_parallel": true, "self": 21.339705581976688, "children": { "_process_rank_one_or_two_observation": { "total": 83.1501548280568, "count": 505712, "is_parallel": true, "self": 83.1501548280568 } } } } } } } } } } }, "trainer_advance": { "total": 633.0569548409735, "count": 63215, "self": 2.6480756079894263, "children": { "process_trajectory": { "total": 124.91409228298494, "count": 63215, "self": 124.6161696259851, "children": { "RLTrainer._checkpoint": { "total": 0.29792265699984455, "count": 2, "self": 0.29792265699984455 } } }, "_update_policy": { "total": 505.49478694999914, "count": 421, "self": 298.3960443060096, "children": { "TorchPPOOptimizer.update": { "total": 207.0987426439895, "count": 22878, "self": 207.0987426439895 } } } } } } }, "trainer_threads": { "total": 1.0090002433571499e-06, "count": 1, "self": 1.0090002433571499e-06 }, "TrainerController._save_models": { "total": 0.0779869799998778, "count": 1, "self": 0.001388613000017358, "children": { "RLTrainer._checkpoint": { "total": 0.07659836699986045, "count": 1, "self": 0.07659836699986045 } } } } } } }