{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9657369256019592, "min": 0.9657369256019592, "max": 2.859520435333252, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9220.8564453125, "min": 9220.8564453125, "max": 29315.802734375, "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": 12.88480281829834, "min": 0.4356588125228882, "max": 12.899770736694336, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2512.53662109375, "min": 84.51780700683594, "max": 2631.55322265625, "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": 0.06738788239154553, "min": 0.06389158351766858, "max": 0.0731515247274479, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2695515295661821, "min": 0.26773115738600894, "max": 0.35614045102471104, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20728813389352724, "min": 0.11936460247299835, "max": 0.31167198038276506, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.829152535574109, "min": 0.4774584098919934, "max": 1.3173407196414237, "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": 25.0, "min": 3.5681818181818183, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 157.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.5681818181818183, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 157.0, "max": 1405.0, "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": "1708515436", "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": "1708515895" }, "total": 459.858125243, "count": 1, "self": 0.4341549070001065, "children": { "run_training.setup": { "total": 0.06772694400001456, "count": 1, "self": 0.06772694400001456 }, "TrainerController.start_learning": { "total": 459.3562433919999, "count": 1, "self": 0.5677194570059783, "children": { "TrainerController._reset_env": { "total": 3.050159697999902, "count": 1, "self": 3.050159697999902 }, "TrainerController.advance": { "total": 455.6452482919941, "count": 18199, "self": 0.286144932998468, "children": { "env_step": { "total": 455.35910335899564, "count": 18199, "self": 295.021178849002, "children": { "SubprocessEnvManager._take_step": { "total": 160.03678067199235, "count": 18199, "self": 1.5292485199984185, "children": { "TorchPolicy.evaluate": { "total": 158.50753215199393, "count": 18199, "self": 158.50753215199393 } } }, "workers": { "total": 0.30114383800128053, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 458.15761124099436, "count": 18199, "is_parallel": true, "self": 228.8656219549996, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005231616999935795, "count": 1, "is_parallel": true, "self": 0.003544500999964839, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016871159999709562, "count": 10, "is_parallel": true, "self": 0.0016871159999709562 } } }, "UnityEnvironment.step": { "total": 0.038953546000016104, "count": 1, "is_parallel": true, "self": 0.0007121959999949468, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004513769999903161, "count": 1, "is_parallel": true, "self": 0.0004513769999903161 }, "communicator.exchange": { "total": 0.03558861400006208, "count": 1, "is_parallel": true, "self": 0.03558861400006208 }, "steps_from_proto": { "total": 0.002201358999968761, "count": 1, "is_parallel": true, "self": 0.0004066639997972743, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017946950001714868, "count": 10, "is_parallel": true, "self": 0.0017946950001714868 } } } } } } }, "UnityEnvironment.step": { "total": 229.29198928599476, "count": 18198, "is_parallel": true, "self": 10.665431616988485, "children": { "UnityEnvironment._generate_step_input": { "total": 5.542341226997337, "count": 18198, "is_parallel": true, "self": 5.542341226997337 }, "communicator.exchange": { "total": 177.32737116799888, "count": 18198, "is_parallel": true, "self": 177.32737116799888 }, "steps_from_proto": { "total": 35.75684527401006, "count": 18198, "is_parallel": true, "self": 6.619110598956354, "children": { "_process_rank_one_or_two_observation": { "total": 29.137734675053707, "count": 181980, "is_parallel": true, "self": 29.137734675053707 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001436249999642314, "count": 1, "self": 0.0001436249999642314, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 449.83300528799896, "count": 670487, "is_parallel": true, "self": 15.020244743982175, "children": { "process_trajectory": { "total": 248.23536665201664, "count": 670487, "is_parallel": true, "self": 247.41246575801642, "children": { "RLTrainer._checkpoint": { "total": 0.8229008940002132, "count": 4, "is_parallel": true, "self": 0.8229008940002132 } } }, "_update_policy": { "total": 186.57739389200015, "count": 90, "is_parallel": true, "self": 52.882488737000585, "children": { "TorchPPOOptimizer.update": { "total": 133.69490515499956, "count": 4587, "is_parallel": true, "self": 133.69490515499956 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09297231999994438, "count": 1, "self": 0.0009900349998588354, "children": { "RLTrainer._checkpoint": { "total": 0.09198228500008554, "count": 1, "self": 0.09198228500008554 } } } } } } }