{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 0.6781819462776184, "min": 0.6781819462776184, "max": 1.4220836162567139, "count": 300 }, "Worm.Policy.Entropy.sum": { "value": 20345.458984375, "min": 20345.458984375, "max": 42662.5078125, "count": 300 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 300 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 300 }, "Worm.Step.mean": { "value": 8999000.0, "min": 29000.0, "max": 8999000.0, "count": 300 }, "Worm.Step.sum": { "value": 8999000.0, "min": 29000.0, "max": 8999000.0, "count": 300 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 251.33346557617188, "min": -0.006610119715332985, "max": 252.6289825439453, "count": 300 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 7540.00390625, "min": -0.1916934698820114, "max": 7578.86962890625, "count": 300 }, "Worm.Environment.CumulativeReward.mean": { "value": 1233.4677083333333, "min": 0.06768914084913659, "max": 1259.4235717773438, "count": 300 }, "Worm.Environment.CumulativeReward.sum": { "value": 37004.03125, "min": 1.962985084624961, "max": 37782.70715332031, "count": 300 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 1233.4677083333333, "min": 0.06768914084913659, "max": 1259.4235717773438, "count": 300 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 37004.03125, "min": 1.962985084624961, "max": 37782.70715332031, "count": 300 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 300 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 300 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.018020539853577724, "min": 0.011846781015589971, "max": 0.02364583143692774, "count": 299 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.018020539853577724, "min": 0.011846781015589971, "max": 0.02364583143692774, "count": 299 }, "Worm.Losses.ValueLoss.mean": { "value": 13.22553893498012, "min": 0.0010078260785944405, "max": 16.18698805854434, "count": 299 }, "Worm.Losses.ValueLoss.sum": { "value": 13.22553893498012, "min": 0.0010078260785944405, "max": 16.18698805854434, "count": 299 }, "Worm.Policy.LearningRate.mean": { "value": 1.0000996666666565e-06, "min": 1.0000996666666565e-06, "max": 0.0002990000003333333, "count": 299 }, "Worm.Policy.LearningRate.sum": { "value": 1.0000996666666565e-06, "min": 1.0000996666666565e-06, "max": 0.0002990000003333333, "count": 299 }, "Worm.Policy.Epsilon.mean": { "value": 0.10033333333333334, "min": 0.10033333333333334, "max": 0.1996666666666667, "count": 299 }, "Worm.Policy.Epsilon.sum": { "value": 0.10033333333333334, "min": 0.10033333333333334, "max": 0.1996666666666667, "count": 299 }, "Worm.Policy.Beta.mean": { "value": 2.663333333333317e-05, "min": 2.663333333333317e-05, "max": 0.004983366666666666, "count": 299 }, "Worm.Policy.Beta.sum": { "value": 2.663333333333317e-05, "min": 2.663333333333317e-05, "max": 0.004983366666666666, "count": 299 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1661031262", "python_version": "3.9.7 | packaged by conda-forge | (default, Sep 29 2021, 19:23:11) \n[GCC 9.4.0]", "command_line_arguments": "/home/studio-lab-user/.conda/envs/d2l/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./trained-envs-executables/linux/Worm/Worm --run-id=Worm 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": "1.21.4", "end_time_seconds": "1661040767" }, "total": 9505.179301352, "count": 1, "self": 0.3217640480015689, "children": { "run_training.setup": { "total": 0.07546858199975759, "count": 1, "self": 0.07546858199975759 }, "TrainerController.start_learning": { "total": 9504.782068722, "count": 1, "self": 13.714989212308865, "children": { "TrainerController._reset_env": { "total": 5.901572881999982, "count": 1, "self": 5.901572881999982 }, "TrainerController.advance": { "total": 9485.044856490691, "count": 901000, "self": 14.444147275373325, "children": { "env_step": { "total": 7610.621874060705, "count": 901000, "self": 6590.342770350579, "children": { "SubprocessEnvManager._take_step": { "total": 1010.656432815174, "count": 901000, "self": 78.82304082228848, "children": { "TorchPolicy.evaluate": { "total": 931.8333919928855, "count": 901000, "self": 226.2188572364612, "children": { "TorchPolicy.sample_actions": { "total": 705.6145347564243, "count": 901000, "self": 705.6145347564243 } } } } }, "workers": { "total": 9.622670894952535, "count": 901000, "self": 0.0, "children": { "worker_root": { "total": 9473.380714820823, "count": 901000, "is_parallel": true, "self": 3752.8072850167464, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008158149998962472, "count": 1, "is_parallel": true, "self": 0.0002778989996841119, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005379160002121353, "count": 2, "is_parallel": true, "self": 0.0005379160002121353 } } }, "UnityEnvironment.step": { "total": 0.022193953999703808, "count": 1, "is_parallel": true, "self": 0.000174381999840989, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043153000024176436, "count": 1, "is_parallel": true, "self": 0.00043153000024176436 }, "communicator.exchange": { "total": 0.02115404899996065, "count": 1, "is_parallel": true, "self": 0.02115404899996065 }, "steps_from_proto": { "total": 0.00043399299966040417, "count": 1, "is_parallel": true, "self": 0.0001865719996203552, "children": { "_process_rank_one_or_two_observation": { "total": 0.00024742100004004897, "count": 2, "is_parallel": true, "self": 0.00024742100004004897 } } } } } } }, "UnityEnvironment.step": { "total": 5720.573429804077, "count": 900999, "is_parallel": true, "self": 124.22179808574037, "children": { "UnityEnvironment._generate_step_input": { "total": 204.84250038642995, "count": 900999, "is_parallel": true, "self": 204.84250038642995 }, "communicator.exchange": { "total": 5091.96472193835, "count": 900999, "is_parallel": true, "self": 5091.96472193835 }, "steps_from_proto": { "total": 299.54440939355663, "count": 900999, "is_parallel": true, "self": 126.6684532889949, "children": { "_process_rank_one_or_two_observation": { "total": 172.87595610456174, "count": 1801998, "is_parallel": true, "self": 172.87595610456174 } } } } } } } } } } }, "trainer_advance": { "total": 1859.978835154613, "count": 901000, "self": 17.128216481557047, "children": { "process_trajectory": { "total": 474.90927054705253, "count": 901000, "self": 472.75272370705125, "children": { "RLTrainer._checkpoint": { "total": 2.1565468400012833, "count": 18, "self": 2.1565468400012833 } } }, "_update_policy": { "total": 1367.9413481260035, "count": 300, "self": 1155.0510788920096, "children": { "TorchPPOOptimizer.update": { "total": 212.89026923399388, "count": 12600, "self": 212.89026923399388 } } } } } } }, "trainer_threads": { "total": 8.879997039912269e-07, "count": 1, "self": 8.879997039912269e-07 }, "TrainerController._save_models": { "total": 0.1206492490000528, "count": 1, "self": 0.0013527459996112157, "children": { "RLTrainer._checkpoint": { "total": 0.11929650300044159, "count": 1, "self": 0.11929650300044159 } } } } } } }