{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0582377910614014, "min": 1.0582377910614014, "max": 2.867619276046753, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10104.0546875, "min": 10104.0546875, "max": 29335.744140625, "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": 12.484735488891602, "min": 0.3966326117515564, "max": 12.484735488891602, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2434.5234375, "min": 76.94672393798828, "max": 2509.40478515625, "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": 0.07366398678933882, "min": 0.06339199106008106, "max": 0.07524886401141902, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29465594715735527, "min": 0.2689922472037485, "max": 0.3707690385031396, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20039382766859204, "min": 0.13015553517513634, "max": 0.28611991861287284, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8015753106743682, "min": 0.5206221407005454, "max": 1.3559179157018661, "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": 24.977272727272727, "min": 3.3636363636363638, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 148.0, "max": 1360.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.3636363636363638, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 148.0, "max": 1360.0, "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": "1679268021", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679268518" }, "total": 496.25972488499997, "count": 1, "self": 0.43096235399991656, "children": { "run_training.setup": { "total": 0.19309771000001774, "count": 1, "self": 0.19309771000001774 }, "TrainerController.start_learning": { "total": 495.63566482100003, "count": 1, "self": 0.579517079007644, "children": { "TrainerController._reset_env": { "total": 8.56081888, "count": 1, "self": 8.56081888 }, "TrainerController.advance": { "total": 486.3494330349924, "count": 18202, "self": 0.30565438699858305, "children": { "env_step": { "total": 486.0437786479938, "count": 18202, "self": 349.55611234799466, "children": { "SubprocessEnvManager._take_step": { "total": 136.19013898199478, "count": 18202, "self": 2.419023044991661, "children": { "TorchPolicy.evaluate": { "total": 133.77111593700312, "count": 18202, "self": 133.77111593700312 } } }, "workers": { "total": 0.29752731800437004, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 494.2169164319922, "count": 18202, "is_parallel": true, "self": 236.84038854299672, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006906451000020297, "count": 1, "is_parallel": true, "self": 0.0043054230000052485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026010280000150487, "count": 10, "is_parallel": true, "self": 0.0026010280000150487 } } }, "UnityEnvironment.step": { "total": 0.047348016000000825, "count": 1, "is_parallel": true, "self": 0.00041136000004371454, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041155599996045567, "count": 1, "is_parallel": true, "self": 0.00041155599996045567 }, "communicator.exchange": { "total": 0.04461397699998315, "count": 1, "is_parallel": true, "self": 0.04461397699998315 }, "steps_from_proto": { "total": 0.0019111230000135038, "count": 1, "is_parallel": true, "self": 0.00038266699999667253, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015284560000168312, "count": 10, "is_parallel": true, "self": 0.0015284560000168312 } } } } } } }, "UnityEnvironment.step": { "total": 257.3765278889955, "count": 18201, "is_parallel": true, "self": 10.124697718988728, "children": { "UnityEnvironment._generate_step_input": { "total": 5.7642933759995, "count": 18201, "is_parallel": true, "self": 5.7642933759995 }, "communicator.exchange": { "total": 206.4914642380113, "count": 18201, "is_parallel": true, "self": 206.4914642380113 }, "steps_from_proto": { "total": 34.996072555995966, "count": 18201, "is_parallel": true, "self": 7.191345130009495, "children": { "_process_rank_one_or_two_observation": { "total": 27.80472742598647, "count": 182010, "is_parallel": true, "self": 27.80472742598647 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010869300001559168, "count": 1, "self": 0.00010869300001559168, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 482.3467190659508, "count": 432701, "is_parallel": true, "self": 11.221002100956639, "children": { "process_trajectory": { "total": 269.6229160889947, "count": 432701, "is_parallel": true, "self": 268.8323084719947, "children": { "RLTrainer._checkpoint": { "total": 0.7906076170000347, "count": 4, "is_parallel": true, "self": 0.7906076170000347 } } }, "_update_policy": { "total": 201.50280087599947, "count": 90, "is_parallel": true, "self": 74.23199692599889, "children": { "TorchPPOOptimizer.update": { "total": 127.27080395000058, "count": 4587, "is_parallel": true, "self": 127.27080395000058 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14578713399998833, "count": 1, "self": 0.0008869629999708195, "children": { "RLTrainer._checkpoint": { "total": 0.1449001710000175, "count": 1, "self": 0.1449001710000175 } } } } } } }