{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8951661586761475, "min": 0.8951661586761475, "max": 2.866051435470581, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8556.8935546875, "min": 8556.8935546875, "max": 29319.70703125, "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": 12.888935089111328, "min": 0.4811691641807556, "max": 12.888935089111328, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2513.34228515625, "min": 93.34681701660156, "max": 2608.209228515625, "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": 0.06884176160897101, "min": 0.06381365417117053, "max": 0.07648191604647425, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27536704643588406, "min": 0.25525461668468213, "max": 0.35972617715528676, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1975298693367079, "min": 0.11672474861409808, "max": 0.26148422639451774, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7901194773468316, "min": 0.4668989944563923, "max": 1.269824141965193, "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": 25.363636363636363, "min": 3.1363636363636362, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 138.0, "max": 1383.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 3.1363636363636362, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 138.0, "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": "1699440588", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699441056" }, "total": 467.5804492490001, "count": 1, "self": 0.43568718800003126, "children": { "run_training.setup": { "total": 0.04506815100000949, "count": 1, "self": 0.04506815100000949 }, "TrainerController.start_learning": { "total": 467.09969391000004, "count": 1, "self": 0.5367051130061782, "children": { "TrainerController._reset_env": { "total": 7.844380935999993, "count": 1, "self": 7.844380935999993 }, "TrainerController.advance": { "total": 458.62691490899385, "count": 18201, "self": 0.25733623499365876, "children": { "env_step": { "total": 458.3695786740002, "count": 18201, "self": 311.2005925600181, "children": { "SubprocessEnvManager._take_step": { "total": 146.88929114399053, "count": 18201, "self": 1.4285711730005346, "children": { "TorchPolicy.evaluate": { "total": 145.46071997099, "count": 18201, "self": 145.46071997099 } } }, "workers": { "total": 0.2796949699915672, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 465.88208095800576, "count": 18201, "is_parallel": true, "self": 228.23919425799346, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0046976410000070246, "count": 1, "is_parallel": true, "self": 0.0032599399999071466, "children": { "_process_rank_one_or_two_observation": { "total": 0.001437701000099878, "count": 10, "is_parallel": true, "self": 0.001437701000099878 } } }, "UnityEnvironment.step": { "total": 0.08408162700004596, "count": 1, "is_parallel": true, "self": 0.0006800450000810088, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003669359999776134, "count": 1, "is_parallel": true, "self": 0.0003669359999776134 }, "communicator.exchange": { "total": 0.08102046800001972, "count": 1, "is_parallel": true, "self": 0.08102046800001972 }, "steps_from_proto": { "total": 0.0020141779999676146, "count": 1, "is_parallel": true, "self": 0.0004130229998509094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016011550001167052, "count": 10, "is_parallel": true, "self": 0.0016011550001167052 } } } } } } }, "UnityEnvironment.step": { "total": 237.6428867000123, "count": 18200, "is_parallel": true, "self": 10.613384398005053, "children": { "UnityEnvironment._generate_step_input": { "total": 5.477643014996033, "count": 18200, "is_parallel": true, "self": 5.477643014996033 }, "communicator.exchange": { "total": 186.81333051400588, "count": 18200, "is_parallel": true, "self": 186.81333051400588 }, "steps_from_proto": { "total": 34.73852877300533, "count": 18200, "is_parallel": true, "self": 6.397492432981153, "children": { "_process_rank_one_or_two_observation": { "total": 28.341036340024175, "count": 182000, "is_parallel": true, "self": 28.341036340024175 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001420050000433548, "count": 1, "self": 0.0001420050000433548, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.7612984089953, "count": 477705, "is_parallel": true, "self": 10.272213954993731, "children": { "process_trajectory": { "total": 258.8984553220023, "count": 477705, "is_parallel": true, "self": 258.3440117630022, "children": { "RLTrainer._checkpoint": { "total": 0.5544435590001058, "count": 4, "is_parallel": true, "self": 0.5544435590001058 } } }, "_update_policy": { "total": 185.59062913199926, "count": 90, "is_parallel": true, "self": 57.247386804003554, "children": { "TorchPPOOptimizer.update": { "total": 128.3432423279957, "count": 4587, "is_parallel": true, "self": 128.3432423279957 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09155094699997335, "count": 1, "self": 0.0008243869999660092, "children": { "RLTrainer._checkpoint": { "total": 0.09072656000000734, "count": 1, "self": 0.09072656000000734 } } } } } } }