{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9376475811004639, "min": 0.9376475811004639, "max": 2.8720340728759766, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8973.287109375, "min": 8973.287109375, "max": 29412.5, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.9743013381958, "min": 0.23325157165527344, "max": 12.9743013381958, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2529.98876953125, "min": 45.25080490112305, "max": 2637.591796875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06774890089410987, "min": 0.05863989823036736, "max": 0.0764375393936301, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2709956035764395, "min": 0.26688399512147276, "max": 0.3821876969681505, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20182303211414346, "min": 0.10052486094668983, "max": 0.28869850999292207, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8072921284565738, "min": 0.4020994437867593, "max": 1.3968061796006033, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.681818181818183, "min": 2.659090909090909, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1130.0, "min": 117.0, "max": 1417.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.681818181818183, "min": 2.659090909090909, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1130.0, "min": 117.0, "max": 1417.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708399441", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708399945" }, "total": 503.871348304, "count": 1, "self": 0.4485946890000605, "children": { "run_training.setup": { "total": 0.053367401000059544, "count": 1, "self": 0.053367401000059544 }, "TrainerController.start_learning": { "total": 503.36938621399986, "count": 1, "self": 0.712355268995907, "children": { "TrainerController._reset_env": { "total": 3.5904459470000347, "count": 1, "self": 3.5904459470000347 }, "TrainerController.advance": { "total": 498.9597013890036, "count": 18200, "self": 0.3697862039892925, "children": { "env_step": { "total": 498.5899151850143, "count": 18200, "self": 323.69254334800394, "children": { "SubprocessEnvManager._take_step": { "total": 174.5284810139924, "count": 18200, "self": 1.737674707008182, "children": { "TorchPolicy.evaluate": { "total": 172.79080630698422, "count": 18200, "self": 172.79080630698422 } } }, "workers": { "total": 0.3688908230179777, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 501.9870766089963, "count": 18200, "is_parallel": true, "self": 246.46624836099113, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005185997000012321, "count": 1, "is_parallel": true, "self": 0.0032785439999543087, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019074530000580125, "count": 10, "is_parallel": true, "self": 0.0019074530000580125 } } }, "UnityEnvironment.step": { "total": 0.08803508000005422, "count": 1, "is_parallel": true, "self": 0.0006618950001211488, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004107199999907607, "count": 1, "is_parallel": true, "self": 0.0004107199999907607 }, "communicator.exchange": { "total": 0.08256470200001331, "count": 1, "is_parallel": true, "self": 0.08256470200001331 }, "steps_from_proto": { "total": 0.004397762999929, "count": 1, "is_parallel": true, "self": 0.00255075500001567, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018470079999133304, "count": 10, "is_parallel": true, "self": 0.0018470079999133304 } } } } } } }, "UnityEnvironment.step": { "total": 255.52082824800516, "count": 18199, "is_parallel": true, "self": 11.955581927018898, "children": { "UnityEnvironment._generate_step_input": { "total": 6.174300566001193, "count": 18199, "is_parallel": true, "self": 6.174300566001193 }, "communicator.exchange": { "total": 198.55088428098668, "count": 18199, "is_parallel": true, "self": 198.55088428098668 }, "steps_from_proto": { "total": 38.84006147399839, "count": 18199, "is_parallel": true, "self": 7.4139802310256755, "children": { "_process_rank_one_or_two_observation": { "total": 31.426081242972714, "count": 181990, "is_parallel": true, "self": 31.426081242972714 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014111000018601771, "count": 1, "self": 0.00014111000018601771, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 492.33438463597804, "count": 755366, "is_parallel": true, "self": 17.313318752968257, "children": { "process_trajectory": { "total": 273.07076987100936, "count": 755366, "is_parallel": true, "self": 272.5322491470092, "children": { "RLTrainer._checkpoint": { "total": 0.5385207240001364, "count": 4, "is_parallel": true, "self": 0.5385207240001364 } } }, "_update_policy": { "total": 201.95029601200042, "count": 90, "is_parallel": true, "self": 55.51631349700608, "children": { "TorchPPOOptimizer.update": { "total": 146.43398251499434, "count": 4587, "is_parallel": true, "self": 146.43398251499434 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10674249900012, "count": 1, "self": 0.0011457890002475324, "children": { "RLTrainer._checkpoint": { "total": 0.10559670999987247, "count": 1, "self": 0.10559670999987247 } } } } } } }