{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.1393401622772217, "min": 0.8784369230270386, "max": 1.4767630100250244, "count": 13 }, "Pyramids.Policy.Entropy.sum": { "value": 34289.58203125, "min": 26816.921875, "max": 44799.08203125, "count": 13 }, "Pyramids.Step.mean": { "value": 389892.0, "min": 29952.0, "max": 389892.0, "count": 13 }, "Pyramids.Step.sum": { "value": 389892.0, "min": 29952.0, "max": 389892.0, "count": 13 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0811186358332634, "min": -0.09695868194103241, "max": -0.059484679251909256, "count": 13 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -19.549591064453125, "min": -23.367042541503906, "max": -14.273317337036133, "count": 13 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01895718090236187, "min": 0.01834954507648945, "max": 0.5088265538215637, "count": 13 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.568680763244629, "min": 4.422240257263184, "max": 120.59188842773438, "count": 13 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06880796320486134, "min": 0.06713543501232867, "max": 0.07518478184371438, "count": 13 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9633114848680586, "min": 0.4991555626259249, "max": 0.9774021639682869, "count": 13 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0011204746355431134, "min": 0.0005412992572571332, "max": 0.009430657141726034, "count": 13 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.01568664489760359, "min": 0.007036890344342732, "max": 0.06601459999208224, "count": 13 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002625531553394285, "min": 0.0002625531553394285, "max": 0.00029838354339596195, "count": 13 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.003675744174751999, "min": 0.0020691136102954665, "max": 0.0039696198767934, "count": 13 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1875177142857143, "min": 0.1875177142857143, "max": 0.19946118095238097, "count": 13 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.625248, "min": 1.3897045333333333, "max": 2.7232066, "count": 13 }, "Pyramids.Policy.Beta.mean": { "value": 0.008753019657142858, "min": 0.008753019657142858, "max": 0.009946171977142856, "count": 13 }, "Pyramids.Policy.Beta.sum": { "value": 0.12254227520000001, "min": 0.06897148288, "max": 0.13232833934000002, "count": 13 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.017215663567185402, "min": 0.017215663567185402, "max": 0.3760848939418793, "count": 13 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24101929366588593, "min": 0.24101929366588593, "max": 2.632594347000122, "count": 13 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 988.25, "min": 907.4375, "max": 999.0, "count": 13 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31624.0, "min": 15984.0, "max": 32439.0, "count": 13 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8014563031028956, "min": -1.0000000521540642, "max": -0.47057504556141794, "count": 13 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -25.64660169929266, "min": -32.000001668930054, "max": -15.058401457965374, "count": 13 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8014563031028956, "min": -1.0000000521540642, "max": -0.47057504556141794, "count": 13 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -25.64660169929266, "min": -32.000001668930054, "max": -15.058401457965374, "count": 13 }, "Pyramids.Policy.RndReward.mean": { "value": 0.18373357944801683, "min": 0.18373357944801683, "max": 7.275272320024669, "count": 13 }, "Pyramids.Policy.RndReward.sum": { "value": 5.879474542336538, "min": 5.879474542336538, "max": 116.4043571203947, "count": 13 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 13 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 13 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705945288", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705946209" }, "total": 920.3789021709999, "count": 1, "self": 0.48357766200024344, "children": { "run_training.setup": { "total": 0.05568737300018256, "count": 1, "self": 0.05568737300018256 }, "TrainerController.start_learning": { "total": 919.8396371359995, "count": 1, "self": 0.6868668499291744, "children": { "TrainerController._reset_env": { "total": 2.194167170999208, "count": 1, "self": 2.194167170999208 }, "TrainerController.advance": { "total": 916.9580880060712, "count": 25831, "self": 0.7112355071885759, "children": { "env_step": { "total": 642.4649182829326, "count": 25831, "self": 579.730725387155, "children": { "SubprocessEnvManager._take_step": { "total": 62.30596385796434, "count": 25831, "self": 2.2832127269966804, "children": { "TorchPolicy.evaluate": { "total": 60.02275113096766, "count": 25699, "self": 60.02275113096766 } } }, "workers": { "total": 0.42822903781325294, "count": 25831, "self": 0.0, "children": { "worker_root": { "total": 917.3812426111299, "count": 25831, "is_parallel": true, "self": 394.60158639005203, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021349349999582046, "count": 1, "is_parallel": true, "self": 0.00065407800138928, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014808569985689246, "count": 8, "is_parallel": true, "self": 0.0014808569985689246 } } }, "UnityEnvironment.step": { "total": 0.06054217100063397, "count": 1, "is_parallel": true, "self": 0.000695821000590513, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00051027100016654, "count": 1, "is_parallel": true, "self": 0.00051027100016654 }, "communicator.exchange": { "total": 0.05716970100002072, "count": 1, "is_parallel": true, "self": 0.05716970100002072 }, "steps_from_proto": { "total": 0.002166377999856195, "count": 1, "is_parallel": true, "self": 0.00043967499823338585, "children": { "_process_rank_one_or_two_observation": { "total": 0.001726703001622809, "count": 8, "is_parallel": true, "self": 0.001726703001622809 } } } } } } }, "UnityEnvironment.step": { "total": 522.7796562210779, "count": 25830, "is_parallel": true, "self": 16.21746677603369, "children": { "UnityEnvironment._generate_step_input": { "total": 11.665922188113655, "count": 25830, "is_parallel": true, "self": 11.665922188113655 }, "communicator.exchange": { "total": 447.52332068497617, "count": 25830, "is_parallel": true, "self": 447.52332068497617 }, "steps_from_proto": { "total": 47.372946571954344, "count": 25830, "is_parallel": true, "self": 9.703481001854925, "children": { "_process_rank_one_or_two_observation": { "total": 37.66946557009942, "count": 206640, "is_parallel": true, "self": 37.66946557009942 } } } } } } } } } } }, "trainer_advance": { "total": 273.78193421595006, "count": 25831, "self": 1.1323134169506375, "children": { "process_trajectory": { "total": 55.33128354399378, "count": 25831, "self": 55.33128354399378 }, "_update_policy": { "total": 217.31833725500564, "count": 169, "self": 128.64882026591204, "children": { "TorchPPOOptimizer.update": { "total": 88.66951698909361, "count": 9406, "self": 88.66951698909361 } } } } } } }, "trainer_threads": { "total": 1.6189997040783055e-06, "count": 1, "self": 1.6189997040783055e-06 }, "TrainerController._save_models": { "total": 0.0005134900002303766, "count": 1, "self": 2.7367000257072505e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0004861229999733041, "count": 1, "self": 0.0004861229999733041 } } } } } } }