{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8630529046058655, "min": 0.8630529046058655, "max": 2.870469093322754, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8278.4033203125, "min": 8278.4033203125, "max": 29459.625, "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": 11.526309967041016, "min": 0.33224353194236755, "max": 11.526309967041016, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2247.63037109375, "min": 64.45524597167969, "max": 2313.70458984375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06736215662756734, "min": 0.06268328679702702, "max": 0.07412900064282082, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26944862651026935, "min": 0.2507331471881081, "max": 0.3662205480687394, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20218347809186168, "min": 0.13656672568621991, "max": 0.2785624170420216, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8087339123674467, "min": 0.5462669027448797, "max": 1.392812085210108, "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": 22.863636363636363, "min": 3.25, "max": 22.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1006.0, "min": 143.0, "max": 1232.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.863636363636363, "min": 3.25, "max": 22.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1006.0, "min": 143.0, "max": 1232.0, "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": "1690546793", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget-e --no-graphics", "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": "1690547252" }, "total": 458.29421820100004, "count": 1, "self": 0.373321562000001, "children": { "run_training.setup": { "total": 0.035695194000027186, "count": 1, "self": 0.035695194000027186 }, "TrainerController.start_learning": { "total": 457.885201445, "count": 1, "self": 0.6675551019835666, "children": { "TrainerController._reset_env": { "total": 4.569844117000002, "count": 1, "self": 4.569844117000002 }, "TrainerController.advance": { "total": 452.4918776770164, "count": 18205, "self": 0.32074897002689795, "children": { "env_step": { "total": 452.1711287069895, "count": 18205, "self": 324.2135494109898, "children": { "SubprocessEnvManager._take_step": { "total": 127.62497395000173, "count": 18205, "self": 1.839266703999101, "children": { "TorchPolicy.evaluate": { "total": 125.78570724600263, "count": 18205, "self": 125.78570724600263 } } }, "workers": { "total": 0.3326053459979903, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 456.8295435620008, "count": 18205, "is_parallel": true, "self": 228.40623359998767, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00643699599993397, "count": 1, "is_parallel": true, "self": 0.004500973999824964, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019360220001090056, "count": 10, "is_parallel": true, "self": 0.0019360220001090056 } } }, "UnityEnvironment.step": { "total": 0.02840804900006333, "count": 1, "is_parallel": true, "self": 0.0004401770000868055, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003064279999307473, "count": 1, "is_parallel": true, "self": 0.0003064279999307473 }, "communicator.exchange": { "total": 0.02623987300000863, "count": 1, "is_parallel": true, "self": 0.02623987300000863 }, "steps_from_proto": { "total": 0.0014215710000371473, "count": 1, "is_parallel": true, "self": 0.0003689530002475294, "children": { "_process_rank_one_or_two_observation": { "total": 0.001052617999789618, "count": 10, "is_parallel": true, "self": 0.001052617999789618 } } } } } } }, "UnityEnvironment.step": { "total": 228.42330996201315, "count": 18204, "is_parallel": true, "self": 10.867723469016482, "children": { "UnityEnvironment._generate_step_input": { "total": 5.646189079983856, "count": 18204, "is_parallel": true, "self": 5.646189079983856 }, "communicator.exchange": { "total": 177.59889544699945, "count": 18204, "is_parallel": true, "self": 177.59889544699945 }, "steps_from_proto": { "total": 34.31050196601336, "count": 18204, "is_parallel": true, "self": 6.347241799073117, "children": { "_process_rank_one_or_two_observation": { "total": 27.963260166940245, "count": 182040, "is_parallel": true, "self": 27.963260166940245 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016909200007830805, "count": 1, "self": 0.00016909200007830805, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 450.713582620014, "count": 256332, "is_parallel": true, "self": 5.952857921976829, "children": { "process_trajectory": { "total": 249.79738773703718, "count": 256332, "is_parallel": true, "self": 248.86503271903723, "children": { "RLTrainer._checkpoint": { "total": 0.9323550179999529, "count": 4, "is_parallel": true, "self": 0.9323550179999529 } } }, "_update_policy": { "total": 194.96333696099998, "count": 90, "is_parallel": true, "self": 51.991214745004186, "children": { "TorchPPOOptimizer.update": { "total": 142.9721222159958, "count": 4587, "is_parallel": true, "self": 142.9721222159958 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1557554569999411, "count": 1, "self": 0.0009539850000237493, "children": { "RLTrainer._checkpoint": { "total": 0.15480147199991734, "count": 1, "self": 0.15480147199991734 } } } } } } }