{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7221418619155884, "min": 0.7221418619155884, "max": 2.8689894676208496, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7435.1728515625, "min": 7435.1728515625, "max": 29381.3203125, "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": 13.121742248535156, "min": 0.26088711619377136, "max": 13.121742248535156, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2558.73974609375, "min": 50.61210250854492, "max": 2672.35595703125, "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": 0.06924631987196835, "min": 0.06379956325599422, "max": 0.07606701298651637, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3462315993598417, "min": 0.2572588377692691, "max": 0.3604726631373541, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20089483268047664, "min": 0.08100316773611577, "max": 0.2909854442465539, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0044741634023833, "min": 0.32401267094446307, "max": 1.4549272212327695, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.470497843200002e-06, "min": 6.470497843200002e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.235248921600001e-05, "min": 3.235248921600001e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1021568, "min": 0.1021568, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.510784, "min": 0.45037600000000005, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00011762432000000005, "min": 0.00011762432000000005, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005881216000000002, "min": 0.0005881216000000002, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.227272727272727, "min": 2.5681818181818183, "max": 26.054545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 113.0, "max": 1433.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 2.5681818181818183, "max": 26.054545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 113.0, "max": 1433.0, "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": "1709027521", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709027985" }, "total": 463.20639897, "count": 1, "self": 0.43714520799994716, "children": { "run_training.setup": { "total": 0.05380405500000052, "count": 1, "self": 0.05380405500000052 }, "TrainerController.start_learning": { "total": 462.71544970700006, "count": 1, "self": 0.6723056849891691, "children": { "TrainerController._reset_env": { "total": 3.530282145000001, "count": 1, "self": 3.530282145000001 }, "TrainerController.advance": { "total": 458.41434452501096, "count": 18264, "self": 0.28649868900185993, "children": { "env_step": { "total": 458.1278458360091, "count": 18264, "self": 296.8161811049994, "children": { "SubprocessEnvManager._take_step": { "total": 161.0090596930072, "count": 18264, "self": 1.5489252960062458, "children": { "TorchPolicy.evaluate": { "total": 159.46013439700096, "count": 18264, "self": 159.46013439700096 } } }, "workers": { "total": 0.30260503800252536, "count": 18264, "self": 0.0, "children": { "worker_root": { "total": 461.1615137610013, "count": 18264, "is_parallel": true, "self": 229.11384325400343, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0062408960000084335, "count": 1, "is_parallel": true, "self": 0.004497001000117962, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017438949998904718, "count": 10, "is_parallel": true, "self": 0.0017438949998904718 } } }, "UnityEnvironment.step": { "total": 0.03903500600006282, "count": 1, "is_parallel": true, "self": 0.0006883269999207187, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044361300001583004, "count": 1, "is_parallel": true, "self": 0.00044361300001583004 }, "communicator.exchange": { "total": 0.035946097000078225, "count": 1, "is_parallel": true, "self": 0.035946097000078225 }, "steps_from_proto": { "total": 0.0019569690000480477, "count": 1, "is_parallel": true, "self": 0.00036710200026845996, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015898669997795878, "count": 10, "is_parallel": true, "self": 0.0015898669997795878 } } } } } } }, "UnityEnvironment.step": { "total": 232.04767050699786, "count": 18263, "is_parallel": true, "self": 11.241520145988488, "children": { "UnityEnvironment._generate_step_input": { "total": 5.70077169500837, "count": 18263, "is_parallel": true, "self": 5.70077169500837 }, "communicator.exchange": { "total": 179.919790940001, "count": 18263, "is_parallel": true, "self": 179.919790940001 }, "steps_from_proto": { "total": 35.185587725999994, "count": 18263, "is_parallel": true, "self": 6.632956863969412, "children": { "_process_rank_one_or_two_observation": { "total": 28.552630862030583, "count": 182630, "is_parallel": true, "self": 28.552630862030583 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.000702790999980607, "count": 1, "self": 0.000702790999980607, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 452.80382940005916, "count": 696872, "is_parallel": true, "self": 14.999771687068346, "children": { "process_trajectory": { "total": 247.49925896399031, "count": 696872, "is_parallel": true, "self": 246.35548472399034, "children": { "RLTrainer._checkpoint": { "total": 1.1437742399999706, "count": 4, "is_parallel": true, "self": 1.1437742399999706 } } }, "_update_policy": { "total": 190.3047987490005, "count": 91, "is_parallel": true, "self": 54.827092441001355, "children": { "TorchPPOOptimizer.update": { "total": 135.47770630799914, "count": 4635, "is_parallel": true, "self": 135.47770630799914 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09781456099995012, "count": 1, "self": 0.001040862999957426, "children": { "RLTrainer._checkpoint": { "total": 0.09677369799999269, "count": 1, "self": 0.09677369799999269 } } } } } } }