{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7823862433433533, "min": 0.7754074335098267, "max": 2.87212872505188, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6962.455078125, "min": 6900.3505859375, "max": 31340.669921875, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399928.0, "min": 9952.0, "max": 399928.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399928.0, "min": 9952.0, "max": 399928.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.034942626953125, "min": 0.45372357964515686, "max": 12.034942626953125, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1733.03173828125, "min": 65.33619689941406, "max": 1863.9541015625, "count": 40 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 0.705839991569519, "min": 0.15340012311935425, "max": 1.2888423204421997, "count": 40 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 101.64096069335938, "min": 22.089616775512695, "max": 197.5901641845703, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06742327443161604, "min": 0.0635198512355975, "max": 0.07569230777824379, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26969309772646416, "min": 0.25407940494239, "max": 0.3784615388912189, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.0851801988285254, "min": 0.05186068983508877, "max": 0.10859993385041461, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.3407207953141016, "min": 0.20744275934035508, "max": 0.5272768591256702, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.825098724999996e-06, "min": 3.825098724999996e-06, "max": 0.000295941001353, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5300394899999985e-05, "min": 1.5300394899999985e-05, "max": 0.00144225001925, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10191249999999999, "min": 0.10191249999999999, "max": 0.2479705, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40764999999999996, "min": 0.40764999999999996, "max": 1.221125, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.362249999999992e-05, "min": 7.362249999999992e-05, "max": 0.0049324853, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0002944899999999997, "min": 0.0002944899999999997, "max": 0.024039425, "count": 40 }, "SnowballTarget.Losses.CuriosityForwardLoss.mean": { "value": 0.04188172720810946, "min": 0.033935607860193534, "max": 0.08911535578560742, "count": 40 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.16752690883243784, "min": 0.13837627082624857, "max": 0.3564614231424297, "count": 40 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 0.6003185132847113, "min": 0.5939198171391207, "max": 2.693057048539905, "count": 40 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 2.4012740531388452, "min": 2.4012740531388452, "max": 11.969808614955229, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.931818181818183, "min": 3.25, "max": 26.204545454545453, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1141.0, "min": 143.0, "max": 1441.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.338635753501546, "min": 2.9249998954209415, "max": 23.584090276197955, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1026.899973154068, "min": 128.69999539852142, "max": 1296.8999617099762, "count": 40 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 1.5325787596997211, "min": 1.4327925314618783, "max": 2.6246763768859886, "count": 40 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 67.43346542678773, "min": 63.73716417513788, "max": 144.35720072872937, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689921905", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ppo_snowballtarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTargetCurious --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1689923075" }, "total": 1170.717425587999, "count": 1, "self": 0.42497604499931185, "children": { "run_training.setup": { "total": 0.03128317899972899, "count": 1, "self": 0.03128317899972899 }, "TrainerController.start_learning": { "total": 1170.261166364, "count": 1, "self": 1.0667345250103608, "children": { "TrainerController._reset_env": { "total": 4.5801261289998365, "count": 1, "self": 4.5801261289998365 }, "TrainerController.advance": { "total": 1164.4760683689901, "count": 36412, "self": 0.5050375901291773, "children": { "env_step": { "total": 1163.971030778861, "count": 36412, "self": 873.7409455367024, "children": { "SubprocessEnvManager._take_step": { "total": 289.68929279413896, "count": 36412, "self": 3.2346155361719866, "children": { "TorchPolicy.evaluate": { "total": 286.454677257967, "count": 36412, "self": 286.454677257967 } } }, "workers": { "total": 0.5407924480196016, "count": 36412, "self": 0.0, "children": { "worker_root": { "total": 1167.2430328119744, "count": 36412, "is_parallel": true, "self": 681.4198886719532, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018927660003100755, "count": 1, "is_parallel": true, "self": 0.000562683999305591, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013300820010044845, "count": 10, "is_parallel": true, "self": 0.0013300820010044845 } } }, "UnityEnvironment.step": { "total": 0.06856268100000307, "count": 1, "is_parallel": true, "self": 0.0005964209994999692, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003943410001738812, "count": 1, "is_parallel": true, "self": 0.0003943410001738812 }, "communicator.exchange": { "total": 0.06546917000014219, "count": 1, "is_parallel": true, "self": 0.06546917000014219 }, "steps_from_proto": { "total": 0.002102749000187032, "count": 1, "is_parallel": true, "self": 0.0005411560005086358, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015615929996783962, "count": 10, "is_parallel": true, "self": 0.0015615929996783962 } } } } } } }, "UnityEnvironment.step": { "total": 485.8231441400212, "count": 36411, "is_parallel": true, "self": 20.639413553023587, "children": { "UnityEnvironment._generate_step_input": { "total": 10.078052166051748, "count": 36411, "is_parallel": true, "self": 10.078052166051748 }, "communicator.exchange": { "total": 387.16746825984774, "count": 36411, "is_parallel": true, "self": 387.16746825984774 }, "steps_from_proto": { "total": 67.93821016109814, "count": 36411, "is_parallel": true, "self": 12.569071423020432, "children": { "_process_rank_one_or_two_observation": { "total": 55.36913873807771, "count": 364110, "is_parallel": true, "self": 55.36913873807771 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020994999977119733, "count": 1, "self": 0.00020994999977119733, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1165.3188830539748, "count": 22648, "is_parallel": true, "self": 0.5316522920466014, "children": { "process_trajectory": { "total": 165.31442269693162, "count": 22648, "is_parallel": true, "self": 155.09521240393315, "children": { "RLTrainer._checkpoint": { "total": 10.219210292998469, "count": 40, "is_parallel": true, "self": 10.219210292998469 } } }, "_update_policy": { "total": 999.4728080649966, "count": 181, "is_parallel": true, "self": 622.892439668005, "children": { "TorchPPOOptimizer.update": { "total": 376.5803683969916, "count": 15380, "is_parallel": true, "self": 376.5803683969916 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13802739099992323, "count": 1, "self": 0.0007361719999607885, "children": { "RLTrainer._checkpoint": { "total": 0.13729121899996244, "count": 1, "self": 0.13729121899996244 } } } } } } }