{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0159817934036255, "min": 1.015092134475708, "max": 2.8699049949645996, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9711.7705078125, "min": 9711.7705078125, "max": 29453.8359375, "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": 12.74387264251709, "min": 0.5165995955467224, "max": 12.74387264251709, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2485.05517578125, "min": 100.22032165527344, "max": 2550.750244140625, "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": 0.059251733342606194, "min": 0.059251733342606194, "max": 0.07384499349441909, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.23700693337042478, "min": 0.23700693337042478, "max": 0.3683792985370839, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18185826730640495, "min": 0.12162535851273465, "max": 0.29134418625457614, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7274330692256198, "min": 0.4865014340509386, "max": 1.2971728251260868, "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": 3.6363636363636362, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 160.0, "max": 1383.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.6363636363636362, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 160.0, "max": 1383.0, "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": "1702392565", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702393150" }, "total": 585.153563474, "count": 1, "self": 0.5916272019999269, "children": { "run_training.setup": { "total": 0.059546909000005144, "count": 1, "self": 0.059546909000005144 }, "TrainerController.start_learning": { "total": 584.502389363, "count": 1, "self": 0.8457652639958724, "children": { "TrainerController._reset_env": { "total": 3.3920165489999476, "count": 1, "self": 3.3920165489999476 }, "TrainerController.advance": { "total": 580.170794437004, "count": 18201, "self": 0.4127683180057602, "children": { "env_step": { "total": 579.7580261189983, "count": 18201, "self": 456.14185722100035, "children": { "SubprocessEnvManager._take_step": { "total": 123.20308644000244, "count": 18201, "self": 2.12295190899556, "children": { "TorchPolicy.evaluate": { "total": 121.08013453100688, "count": 18201, "self": 121.08013453100688 } } }, "workers": { "total": 0.41308245799547194, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 582.5328291849914, "count": 18201, "is_parallel": true, "self": 266.88619712398923, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005363224999996419, "count": 1, "is_parallel": true, "self": 0.0028959559999748308, "children": { "_process_rank_one_or_two_observation": { "total": 0.002467269000021588, "count": 10, "is_parallel": true, "self": 0.002467269000021588 } } }, "UnityEnvironment.step": { "total": 0.07668238700000529, "count": 1, "is_parallel": true, "self": 0.0007599039999490742, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004158840000059172, "count": 1, "is_parallel": true, "self": 0.0004158840000059172 }, "communicator.exchange": { "total": 0.07332217100002936, "count": 1, "is_parallel": true, "self": 0.07332217100002936 }, "steps_from_proto": { "total": 0.0021844280000209437, "count": 1, "is_parallel": true, "self": 0.0003930670000613645, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017913609999595792, "count": 10, "is_parallel": true, "self": 0.0017913609999595792 } } } } } } }, "UnityEnvironment.step": { "total": 315.6466320610022, "count": 18200, "is_parallel": true, "self": 14.115496107000524, "children": { "UnityEnvironment._generate_step_input": { "total": 7.705485474991917, "count": 18200, "is_parallel": true, "self": 7.705485474991917 }, "communicator.exchange": { "total": 248.65586069600778, "count": 18200, "is_parallel": true, "self": 248.65586069600778 }, "steps_from_proto": { "total": 45.16978978300199, "count": 18200, "is_parallel": true, "self": 8.792270498991456, "children": { "_process_rank_one_or_two_observation": { "total": 36.37751928401053, "count": 182000, "is_parallel": true, "self": 36.37751928401053 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.000756384000055732, "count": 1, "self": 0.000756384000055732, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 575.026404663023, "count": 601928, "is_parallel": true, "self": 13.879202484035432, "children": { "process_trajectory": { "total": 317.0609759429868, "count": 601928, "is_parallel": true, "self": 316.5471940069867, "children": { "RLTrainer._checkpoint": { "total": 0.5137819360001004, "count": 4, "is_parallel": true, "self": 0.5137819360001004 } } }, "_update_policy": { "total": 244.0862262360007, "count": 90, "is_parallel": true, "self": 73.570634915999, "children": { "TorchPPOOptimizer.update": { "total": 170.5155913200017, "count": 4587, "is_parallel": true, "self": 170.5155913200017 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09305672900006812, "count": 1, "self": 0.0011439560000781057, "children": { "RLTrainer._checkpoint": { "total": 0.09191277299999001, "count": 1, "self": 0.09191277299999001 } } } } } } }