{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8285091519355774, "min": 0.8165498375892639, "max": 2.8554112911224365, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7910.60546875, "min": 7910.60546875, "max": 29273.677734375, "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": 12.770590782165527, "min": 0.4351233243942261, "max": 12.770590782165527, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2490.26513671875, "min": 84.41392517089844, "max": 2613.099365234375, "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": 0.06771687565196771, "min": 0.061401630520669964, "max": 0.07312868266698762, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27086750260787085, "min": 0.24560652208267986, "max": 0.3582391675679223, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1979734380455578, "min": 0.09601693931515055, "max": 0.2913964162854587, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7918937521822312, "min": 0.3840677572606022, "max": 1.4569820814272936, "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": 0.001385256038248, "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": 0.961752, "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": 0.0230914248, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.636363636363637, "min": 3.0681818181818183, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1084.0, "min": 135.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.636363636363637, "min": 3.0681818181818183, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1084.0, "min": 135.0, "max": 1390.0, "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": "1707373011", "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": "1707373493" }, "total": 482.1834616809999, "count": 1, "self": 0.4388804029999278, "children": { "run_training.setup": { "total": 0.05030994099996633, "count": 1, "self": 0.05030994099996633 }, "TrainerController.start_learning": { "total": 481.69427133700003, "count": 1, "self": 0.6157540050070338, "children": { "TrainerController._reset_env": { "total": 3.9616631289999873, "count": 1, "self": 3.9616631289999873 }, "TrainerController.advance": { "total": 477.0247452669931, "count": 18200, "self": 0.2997630049891882, "children": { "env_step": { "total": 476.7249822620039, "count": 18200, "self": 309.004646249004, "children": { "SubprocessEnvManager._take_step": { "total": 167.39694554000533, "count": 18200, "self": 1.5787248890098908, "children": { "TorchPolicy.evaluate": { "total": 165.81822065099544, "count": 18200, "self": 165.81822065099544 } } }, "workers": { "total": 0.3233904729945607, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 480.3478193909998, "count": 18200, "is_parallel": true, "self": 237.7628350530049, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005705104000014671, "count": 1, "is_parallel": true, "self": 0.004106535000005351, "children": { "_process_rank_one_or_two_observation": { "total": 0.00159856900000932, "count": 10, "is_parallel": true, "self": 0.00159856900000932 } } }, "UnityEnvironment.step": { "total": 0.043505696000011085, "count": 1, "is_parallel": true, "self": 0.0008049519999531185, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005127450000372846, "count": 1, "is_parallel": true, "self": 0.0005127450000372846 }, "communicator.exchange": { "total": 0.039704819000007774, "count": 1, "is_parallel": true, "self": 0.039704819000007774 }, "steps_from_proto": { "total": 0.002483180000012908, "count": 1, "is_parallel": true, "self": 0.000481443999944986, "children": { "_process_rank_one_or_two_observation": { "total": 0.002001736000067922, "count": 10, "is_parallel": true, "self": 0.002001736000067922 } } } } } } }, "UnityEnvironment.step": { "total": 242.5849843379949, "count": 18199, "is_parallel": true, "self": 11.601160779989414, "children": { "UnityEnvironment._generate_step_input": { "total": 5.960717912996813, "count": 18199, "is_parallel": true, "self": 5.960717912996813 }, "communicator.exchange": { "total": 187.2752166270041, "count": 18199, "is_parallel": true, "self": 187.2752166270041 }, "steps_from_proto": { "total": 37.74788901800457, "count": 18199, "is_parallel": true, "self": 6.987348224989944, "children": { "_process_rank_one_or_two_observation": { "total": 30.760540793014627, "count": 181990, "is_parallel": true, "self": 30.760540793014627 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013341299995772715, "count": 1, "self": 0.00013341299995772715, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 470.76064889798977, "count": 719324, "is_parallel": true, "self": 16.189526099057332, "children": { "process_trajectory": { "total": 261.1784381069323, "count": 719324, "is_parallel": true, "self": 260.64203366293225, "children": { "RLTrainer._checkpoint": { "total": 0.5364044440000271, "count": 4, "is_parallel": true, "self": 0.5364044440000271 } } }, "_update_policy": { "total": 193.39268469200016, "count": 90, "is_parallel": true, "self": 54.17852410900201, "children": { "TorchPPOOptimizer.update": { "total": 139.21416058299815, "count": 4584, "is_parallel": true, "self": 139.21416058299815 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09197552299997369, "count": 1, "self": 0.0009376809999821489, "children": { "RLTrainer._checkpoint": { "total": 0.09103784199999154, "count": 1, "self": 0.09103784199999154 } } } } } } }