{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9048017263412476, "min": 0.9031973481178284, "max": 2.860398054122925, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8639.046875, "min": 8639.046875, "max": 29356.265625, "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": 12.831603050231934, "min": 0.47964712977409363, "max": 12.831603050231934, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2502.16259765625, "min": 93.05154418945312, "max": 2604.206787109375, "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": 0.07177659686538962, "min": 0.06273612759518894, "max": 0.0761423592056221, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2871063874615585, "min": 0.25094451038075577, "max": 0.38071179602811045, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1909703147031513, "min": 0.14052246483362407, "max": 0.268650480929543, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7638812588126052, "min": 0.5620898593344963, "max": 1.3398533714752572, "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": 25.477272727272727, "min": 3.840909090909091, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 169.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.840909090909091, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 169.0, "max": 1403.0, "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": "1680879460", "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": "1680879933" }, "total": 473.3076302360001, "count": 1, "self": 0.7405562570000939, "children": { "run_training.setup": { "total": 0.10851998900000126, "count": 1, "self": 0.10851998900000126 }, "TrainerController.start_learning": { "total": 472.45855399, "count": 1, "self": 0.6267908539954306, "children": { "TrainerController._reset_env": { "total": 4.882289539999988, "count": 1, "self": 4.882289539999988 }, "TrainerController.advance": { "total": 466.7444639270046, "count": 18213, "self": 0.2880137960086131, "children": { "env_step": { "total": 466.45645013099596, "count": 18213, "self": 339.65151581100474, "children": { "SubprocessEnvManager._take_step": { "total": 126.52331820399331, "count": 18213, "self": 1.866870090007069, "children": { "TorchPolicy.evaluate": { "total": 124.65644811398624, "count": 18213, "self": 124.65644811398624 } } }, "workers": { "total": 0.28161611599790604, "count": 18213, "self": 0.0, "children": { "worker_root": { "total": 470.8756124520048, "count": 18213, "is_parallel": true, "self": 218.59509072600338, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006062379000013607, "count": 1, "is_parallel": true, "self": 0.004325905000030161, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017364739999834455, "count": 10, "is_parallel": true, "self": 0.0017364739999834455 } } }, "UnityEnvironment.step": { "total": 0.09657549799999288, "count": 1, "is_parallel": true, "self": 0.0006581029999779275, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004313289999799963, "count": 1, "is_parallel": true, "self": 0.0004313289999799963 }, "communicator.exchange": { "total": 0.0879253610000319, "count": 1, "is_parallel": true, "self": 0.0879253610000319 }, "steps_from_proto": { "total": 0.007560705000003054, "count": 1, "is_parallel": true, "self": 0.0004685799999606388, "children": { "_process_rank_one_or_two_observation": { "total": 0.007092125000042415, "count": 10, "is_parallel": true, "self": 0.007092125000042415 } } } } } } }, "UnityEnvironment.step": { "total": 252.28052172600144, "count": 18212, "is_parallel": true, "self": 10.029773429992758, "children": { "UnityEnvironment._generate_step_input": { "total": 5.626000032995478, "count": 18212, "is_parallel": true, "self": 5.626000032995478 }, "communicator.exchange": { "total": 203.16810579401022, "count": 18212, "is_parallel": true, "self": 203.16810579401022 }, "steps_from_proto": { "total": 33.456642469002986, "count": 18212, "is_parallel": true, "self": 6.771910743993317, "children": { "_process_rank_one_or_two_observation": { "total": 26.68473172500967, "count": 182120, "is_parallel": true, "self": 26.68473172500967 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016299999992952507, "count": 1, "self": 0.00016299999992952507, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 462.90583009897466, "count": 420095, "is_parallel": true, "self": 10.89416382604901, "children": { "process_trajectory": { "total": 255.512610058926, "count": 420095, "is_parallel": true, "self": 253.52481563092607, "children": { "RLTrainer._checkpoint": { "total": 1.9877944279999156, "count": 4, "is_parallel": true, "self": 1.9877944279999156 } } }, "_update_policy": { "total": 196.49905621399967, "count": 90, "is_parallel": true, "self": 71.46288528900573, "children": { "TorchPPOOptimizer.update": { "total": 125.03617092499394, "count": 4587, "is_parallel": true, "self": 125.03617092499394 } } } } } } } } }, "TrainerController._save_models": { "total": 0.20484666900006232, "count": 1, "self": 0.0011457820000941865, "children": { "RLTrainer._checkpoint": { "total": 0.20370088699996813, "count": 1, "self": 0.20370088699996813 } } } } } } }