{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8703454732894897, "min": 0.8703454732894897, "max": 2.858499765396118, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8329.2060546875, "min": 8329.2060546875, "max": 29273.896484375, "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": 13.149867057800293, "min": 0.40886858105659485, "max": 13.149867057800293, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2564.22412109375, "min": 79.32050323486328, "max": 2662.70703125, "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": 0.07266655977753758, "min": 0.06172953929355002, "max": 0.07469915203960138, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2906662391101503, "min": 0.2573342920252745, "max": 0.3734957601980069, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1911083386809218, "min": 0.12206228794963737, "max": 0.29627418466934974, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7644333547236872, "min": 0.4882491517985495, "max": 1.3306385328372319, "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": 25.931818181818183, "min": 3.477272727272727, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1141.0, "min": 153.0, "max": 1418.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.931818181818183, "min": 3.477272727272727, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1141.0, "min": 153.0, "max": 1418.0, "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": "1704406905", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704407342" }, "total": 436.9577309749999, "count": 1, "self": 0.451784077999946, "children": { "run_training.setup": { "total": 0.05873972300003061, "count": 1, "self": 0.05873972300003061 }, "TrainerController.start_learning": { "total": 436.4472071739999, "count": 1, "self": 0.548649678986294, "children": { "TrainerController._reset_env": { "total": 4.132958492000057, "count": 1, "self": 4.132958492000057 }, "TrainerController.advance": { "total": 431.6803771540134, "count": 18200, "self": 0.2567184320180331, "children": { "env_step": { "total": 431.42365872199537, "count": 18200, "self": 283.041403214026, "children": { "SubprocessEnvManager._take_step": { "total": 148.00208521199283, "count": 18200, "self": 1.439715575982632, "children": { "TorchPolicy.evaluate": { "total": 146.5623696360102, "count": 18200, "self": 146.5623696360102 } } }, "workers": { "total": 0.38017029597654073, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 435.2602726260011, "count": 18200, "is_parallel": true, "self": 214.5185980799953, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007107311000027039, "count": 1, "is_parallel": true, "self": 0.005745494000166218, "children": { "_process_rank_one_or_two_observation": { "total": 0.001361816999860821, "count": 10, "is_parallel": true, "self": 0.001361816999860821 } } }, "UnityEnvironment.step": { "total": 0.0361887530000331, "count": 1, "is_parallel": true, "self": 0.0006390359999386419, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040087600007154833, "count": 1, "is_parallel": true, "self": 0.00040087600007154833 }, "communicator.exchange": { "total": 0.03323738900007811, "count": 1, "is_parallel": true, "self": 0.03323738900007811 }, "steps_from_proto": { "total": 0.001911451999944802, "count": 1, "is_parallel": true, "self": 0.0003883050001149968, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015231469998298053, "count": 10, "is_parallel": true, "self": 0.0015231469998298053 } } } } } } }, "UnityEnvironment.step": { "total": 220.7416745460058, "count": 18199, "is_parallel": true, "self": 10.564435538002385, "children": { "UnityEnvironment._generate_step_input": { "total": 5.149367574005737, "count": 18199, "is_parallel": true, "self": 5.149367574005737 }, "communicator.exchange": { "total": 172.4228945749951, "count": 18199, "is_parallel": true, "self": 172.4228945749951 }, "steps_from_proto": { "total": 32.60497685900259, "count": 18199, "is_parallel": true, "self": 5.93540165200568, "children": { "_process_rank_one_or_two_observation": { "total": 26.66957520699691, "count": 181990, "is_parallel": true, "self": 26.66957520699691 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001263530000414903, "count": 1, "self": 0.0001263530000414903, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 426.4725346341288, "count": 658240, "is_parallel": true, "self": 14.386961697144784, "children": { "process_trajectory": { "total": 235.01717066998276, "count": 658240, "is_parallel": true, "self": 233.90581797298273, "children": { "RLTrainer._checkpoint": { "total": 1.1113526970000294, "count": 4, "is_parallel": true, "self": 1.1113526970000294 } } }, "_update_policy": { "total": 177.06840226700126, "count": 90, "is_parallel": true, "self": 55.719407132000015, "children": { "TorchPPOOptimizer.update": { "total": 121.34899513500125, "count": 4584, "is_parallel": true, "self": 121.34899513500125 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08509549600012178, "count": 1, "self": 0.0009962010001345334, "children": { "RLTrainer._checkpoint": { "total": 0.08409929499998725, "count": 1, "self": 0.08409929499998725 } } } } } } }