{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0006499290466309, "min": 0.9891956448554993, "max": 2.871330738067627, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9554.2060546875, "min": 9554.2060546875, "max": 29405.296875, "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": 12.943304061889648, "min": 0.2548230290412903, "max": 12.943304061889648, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2523.9443359375, "min": 49.4356689453125, "max": 2606.6884765625, "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": 0.07316008389598744, "min": 0.06105609089390068, "max": 0.07549472379140948, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29264033558394975, "min": 0.24422436357560273, "max": 0.37449633159021867, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18831583039433347, "min": 0.10233536022875056, "max": 0.2785749422276721, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7532633215773339, "min": 0.40934144091500224, "max": 1.3484840679402443, "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": 26.045454545454547, "min": 2.909090909090909, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1146.0, "min": 128.0, "max": 1398.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.045454545454547, "min": 2.909090909090909, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1146.0, "min": 128.0, "max": 1398.0, "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": "1709052998", "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": "1709053422" }, "total": 424.55767669199986, "count": 1, "self": 0.43814967499986324, "children": { "run_training.setup": { "total": 0.07854055300003893, "count": 1, "self": 0.07854055300003893 }, "TrainerController.start_learning": { "total": 424.04098646399996, "count": 1, "self": 0.540105398003675, "children": { "TrainerController._reset_env": { "total": 3.3119715440000164, "count": 1, "self": 3.3119715440000164 }, "TrainerController.advance": { "total": 420.0939386999962, "count": 18199, "self": 0.24913623199870472, "children": { "env_step": { "total": 419.8448024679975, "count": 18199, "self": 269.48179050300814, "children": { "SubprocessEnvManager._take_step": { "total": 150.0913525119937, "count": 18199, "self": 1.3987762909976027, "children": { "TorchPolicy.evaluate": { "total": 148.6925762209961, "count": 18199, "self": 148.6925762209961 } } }, "workers": { "total": 0.27165945299566374, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 422.9764122380012, "count": 18199, "is_parallel": true, "self": 211.58426849599857, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005231857000012496, "count": 1, "is_parallel": true, "self": 0.003663589000098, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015682679999144966, "count": 10, "is_parallel": true, "self": 0.0015682679999144966 } } }, "UnityEnvironment.step": { "total": 0.03989356099998531, "count": 1, "is_parallel": true, "self": 0.0006372629999304991, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003794860000425615, "count": 1, "is_parallel": true, "self": 0.0003794860000425615 }, "communicator.exchange": { "total": 0.03691614800004572, "count": 1, "is_parallel": true, "self": 0.03691614800004572 }, "steps_from_proto": { "total": 0.0019606639999665276, "count": 1, "is_parallel": true, "self": 0.0003841109999029868, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015765530000635408, "count": 10, "is_parallel": true, "self": 0.0015765530000635408 } } } } } } }, "UnityEnvironment.step": { "total": 211.39214374200265, "count": 18198, "is_parallel": true, "self": 10.244944951996672, "children": { "UnityEnvironment._generate_step_input": { "total": 5.146094040995081, "count": 18198, "is_parallel": true, "self": 5.146094040995081 }, "communicator.exchange": { "total": 163.6185018689995, "count": 18198, "is_parallel": true, "self": 163.6185018689995 }, "steps_from_proto": { "total": 32.382602880011405, "count": 18198, "is_parallel": true, "self": 5.859244471954867, "children": { "_process_rank_one_or_two_observation": { "total": 26.523358408056538, "count": 181980, "is_parallel": true, "self": 26.523358408056538 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012179400005152274, "count": 1, "self": 0.00012179400005152274, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 414.5660158709869, "count": 660839, "is_parallel": true, "self": 13.912935161034056, "children": { "process_trajectory": { "total": 228.02885824195346, "count": 660839, "is_parallel": true, "self": 227.56227546195328, "children": { "RLTrainer._checkpoint": { "total": 0.4665827800001807, "count": 4, "is_parallel": true, "self": 0.4665827800001807 } } }, "_update_policy": { "total": 172.6242224679994, "count": 90, "is_parallel": true, "self": 49.802114771001584, "children": { "TorchPPOOptimizer.update": { "total": 122.82210769699782, "count": 4587, "is_parallel": true, "self": 122.82210769699782 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09484902799999873, "count": 1, "self": 0.0009919490000811493, "children": { "RLTrainer._checkpoint": { "total": 0.09385707899991758, "count": 1, "self": 0.09385707899991758 } } } } } } }