{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9011333584785461, "min": 0.9011333584785461, "max": 2.863861322402954, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8604.021484375, "min": 8604.021484375, "max": 29360.306640625, "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": 12.843873023986816, "min": 0.4344838857650757, "max": 12.843873023986816, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2504.55517578125, "min": 84.28987121582031, "max": 2593.699462890625, "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": 0.07052967558468248, "min": 0.06062973385312801, "max": 0.07682464971417087, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28211870233872993, "min": 0.24407442778978933, "max": 0.37819793416579783, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21678111165323677, "min": 0.15262091511805703, "max": 0.2951080462365758, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8671244466129471, "min": 0.6104836604722281, "max": 1.3845663596602047, "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": 25.727272727272727, "min": 3.75, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 165.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.75, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 165.0, "max": 1411.0, "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": "1720125008", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720125503" }, "total": 494.9788190239999, "count": 1, "self": 0.48783703300000525, "children": { "run_training.setup": { "total": 0.09652441599996564, "count": 1, "self": 0.09652441599996564 }, "TrainerController.start_learning": { "total": 494.39445757499993, "count": 1, "self": 0.6268157710023843, "children": { "TrainerController._reset_env": { "total": 3.3216414430000896, "count": 1, "self": 3.3216414430000896 }, "TrainerController.advance": { "total": 490.3513272139976, "count": 18201, "self": 0.3041475279912902, "children": { "env_step": { "total": 490.0471796860063, "count": 18201, "self": 321.7327709589922, "children": { "SubprocessEnvManager._take_step": { "total": 168.00830214600478, "count": 18201, "self": 1.5806369170102244, "children": { "TorchPolicy.evaluate": { "total": 166.42766522899456, "count": 18201, "self": 166.42766522899456 } } }, "workers": { "total": 0.30610658100931687, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 493.10292052299314, "count": 18201, "is_parallel": true, "self": 246.84124654200627, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008025060999898415, "count": 1, "is_parallel": true, "self": 0.0056231240002944105, "children": { "_process_rank_one_or_two_observation": { "total": 0.002401936999604004, "count": 10, "is_parallel": true, "self": 0.002401936999604004 } } }, "UnityEnvironment.step": { "total": 0.0414016569998239, "count": 1, "is_parallel": true, "self": 0.0007003600001098675, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040631299998494796, "count": 1, "is_parallel": true, "self": 0.00040631299998494796 }, "communicator.exchange": { "total": 0.0381708739998885, "count": 1, "is_parallel": true, "self": 0.0381708739998885 }, "steps_from_proto": { "total": 0.0021241099998405844, "count": 1, "is_parallel": true, "self": 0.00042003999988082796, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017040699999597564, "count": 10, "is_parallel": true, "self": 0.0017040699999597564 } } } } } } }, "UnityEnvironment.step": { "total": 246.26167398098687, "count": 18200, "is_parallel": true, "self": 11.046602495013303, "children": { "UnityEnvironment._generate_step_input": { "total": 5.892424778960276, "count": 18200, "is_parallel": true, "self": 5.892424778960276 }, "communicator.exchange": { "total": 191.99821477299542, "count": 18200, "is_parallel": true, "self": 191.99821477299542 }, "steps_from_proto": { "total": 37.324431934017866, "count": 18200, "is_parallel": true, "self": 7.044783705030795, "children": { "_process_rank_one_or_two_observation": { "total": 30.27964822898707, "count": 182000, "is_parallel": true, "self": 30.27964822898707 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020039999981236178, "count": 1, "self": 0.00020039999981236178, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 483.97397674681633, "count": 719638, "is_parallel": true, "self": 16.78261704174861, "children": { "process_trajectory": { "total": 268.33505444106913, "count": 719638, "is_parallel": true, "self": 267.3332967280692, "children": { "RLTrainer._checkpoint": { "total": 1.0017577129999609, "count": 4, "is_parallel": true, "self": 1.0017577129999609 } } }, "_update_policy": { "total": 198.8563052639986, "count": 90, "is_parallel": true, "self": 64.60158270300008, "children": { "TorchPPOOptimizer.update": { "total": 134.25472256099852, "count": 4584, "is_parallel": true, "self": 134.25472256099852 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09447274700005437, "count": 1, "self": 0.0010203560000263678, "children": { "RLTrainer._checkpoint": { "total": 0.093452391000028, "count": 1, "self": 0.093452391000028 } } } } } } }