{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7434178590774536, "min": 0.7307478189468384, "max": 2.861063003540039, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7122.6865234375, "min": 7122.6865234375, "max": 29363.08984375, "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": 12.741947174072266, "min": 0.18098965287208557, "max": 12.741947174072266, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2484.6796875, "min": 35.11199188232422, "max": 2576.37353515625, "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": 0.06521414332254448, "min": 0.06266817213655289, "max": 0.0732034744247429, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2608565732901779, "min": 0.25067268854621155, "max": 0.35586830605804126, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23738424114736856, "min": 0.1128713250201305, "max": 0.26961125133960856, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9495369645894742, "min": 0.451485300080522, "max": 1.34503713425468, "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": 24.681818181818183, "min": 3.3863636363636362, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1086.0, "min": 149.0, "max": 1375.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.681818181818183, "min": 3.3863636363636362, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1086.0, "min": 149.0, "max": 1375.0, "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": "1712434137", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/joeny/.local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=trained-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": "1712434416" }, "total": 279.947967026, "count": 1, "self": 0.24842097199984892, "children": { "run_training.setup": { "total": 0.09307330000001457, "count": 1, "self": 0.09307330000001457 }, "TrainerController.start_learning": { "total": 279.60647275400015, "count": 1, "self": 0.3651284539967037, "children": { "TrainerController._reset_env": { "total": 4.133811033000029, "count": 1, "self": 4.133811033000029 }, "TrainerController.advance": { "total": 275.04964537700334, "count": 18202, "self": 0.18294403599225006, "children": { "env_step": { "total": 274.8667013410111, "count": 18202, "self": 190.95275248304256, "children": { "SubprocessEnvManager._take_step": { "total": 83.71366685899261, "count": 18202, "self": 0.8493777879875779, "children": { "TorchPolicy.evaluate": { "total": 82.86428907100503, "count": 18202, "self": 82.86428907100503 } } }, "workers": { "total": 0.20028199897592458, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 279.2197889370343, "count": 18202, "is_parallel": true, "self": 136.8434852200387, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.012722025000130088, "count": 1, "is_parallel": true, "self": 0.010813682999923913, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019083420002061757, "count": 10, "is_parallel": true, "self": 0.0019083420002061757 } } }, "UnityEnvironment.step": { "total": 0.01878382400013834, "count": 1, "is_parallel": true, "self": 0.000405600000249251, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001622649999717396, "count": 1, "is_parallel": true, "self": 0.0001622649999717396 }, "communicator.exchange": { "total": 0.01683230999992702, "count": 1, "is_parallel": true, "self": 0.01683230999992702 }, "steps_from_proto": { "total": 0.0013836489999903279, "count": 1, "is_parallel": true, "self": 0.0002673410003808385, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011163079996094893, "count": 10, "is_parallel": true, "self": 0.0011163079996094893 } } } } } } }, "UnityEnvironment.step": { "total": 142.3763037169956, "count": 18201, "is_parallel": true, "self": 7.704632839047235, "children": { "UnityEnvironment._generate_step_input": { "total": 3.4844193529929726, "count": 18201, "is_parallel": true, "self": 3.4844193529929726 }, "communicator.exchange": { "total": 110.1179115629759, "count": 18201, "is_parallel": true, "self": 110.1179115629759 }, "steps_from_proto": { "total": 21.069339961979495, "count": 18201, "is_parallel": true, "self": 3.6146566699449068, "children": { "_process_rank_one_or_two_observation": { "total": 17.454683292034588, "count": 182010, "is_parallel": true, "self": 17.454683292034588 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.135999996738974e-05, "count": 1, "self": 8.135999996738974e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 274.5687579019834, "count": 194468, "is_parallel": true, "self": 2.077428733021634, "children": { "process_trajectory": { "total": 158.59931085996232, "count": 194468, "is_parallel": true, "self": 157.99663569796235, "children": { "RLTrainer._checkpoint": { "total": 0.6026751619999686, "count": 4, "is_parallel": true, "self": 0.6026751619999686 } } }, "_update_policy": { "total": 113.89201830899947, "count": 90, "is_parallel": true, "self": 24.571062084993173, "children": { "TorchPPOOptimizer.update": { "total": 89.3209562240063, "count": 4587, "is_parallel": true, "self": 89.3209562240063 } } } } } } } } }, "TrainerController._save_models": { "total": 0.05780653000010716, "count": 1, "self": 0.000611704999982976, "children": { "RLTrainer._checkpoint": { "total": 0.05719482500012418, "count": 1, "self": 0.05719482500012418 } } } } } } }