{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9824436902999878, "min": 0.9724076390266418, "max": 2.8730735778808594, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9423.599609375, "min": 9423.599609375, "max": 29391.54296875, "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": 13.06872272491455, "min": 0.20127679407596588, "max": 13.06872272491455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2548.40087890625, "min": 39.047698974609375, "max": 2645.0791015625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07075197532500241, "min": 0.06638499377432333, "max": 0.07477564468692222, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28300790130000963, "min": 0.2655399750972933, "max": 0.3738782234346111, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18855872501929602, "min": 0.14265220290661662, "max": 0.28112661709972453, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7542349000771841, "min": 0.5706088116264665, "max": 1.4056330854986228, "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": 25.636363636363637, "min": 3.3863636363636362, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1128.0, "min": 149.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.636363636363637, "min": 3.3863636363636362, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1128.0, "min": 149.0, "max": 1402.0, "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": "1679700059", "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": "1679700546" }, "total": 486.66266537999996, "count": 1, "self": 0.7909125649999851, "children": { "run_training.setup": { "total": 0.1253098809999642, "count": 1, "self": 0.1253098809999642 }, "TrainerController.start_learning": { "total": 485.746442934, "count": 1, "self": 0.5996455499987405, "children": { "TrainerController._reset_env": { "total": 8.39204609899997, "count": 1, "self": 8.39204609899997 }, "TrainerController.advance": { "total": 476.53691677000126, "count": 18223, "self": 0.28958522600947845, "children": { "env_step": { "total": 476.2473315439918, "count": 18223, "self": 342.5268519649827, "children": { "SubprocessEnvManager._take_step": { "total": 133.43228400199786, "count": 18223, "self": 2.3591128549947484, "children": { "TorchPolicy.evaluate": { "total": 131.0731711470031, "count": 18223, "self": 131.0731711470031 } } }, "workers": { "total": 0.28819557701120857, "count": 18223, "self": 0.0, "children": { "worker_root": { "total": 484.06515131499634, "count": 18223, "is_parallel": true, "self": 231.82909641198853, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053724929999816595, "count": 1, "is_parallel": true, "self": 0.0038144419999071033, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015580510000745562, "count": 10, "is_parallel": true, "self": 0.0015580510000745562 } } }, "UnityEnvironment.step": { "total": 0.0381427570000028, "count": 1, "is_parallel": true, "self": 0.0005500090000509772, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029950099997222424, "count": 1, "is_parallel": true, "self": 0.00029950099997222424 }, "communicator.exchange": { "total": 0.03531832200002327, "count": 1, "is_parallel": true, "self": 0.03531832200002327 }, "steps_from_proto": { "total": 0.001974924999956329, "count": 1, "is_parallel": true, "self": 0.0003936870000984527, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015812379998578763, "count": 10, "is_parallel": true, "self": 0.0015812379998578763 } } } } } } }, "UnityEnvironment.step": { "total": 252.2360549030078, "count": 18222, "is_parallel": true, "self": 9.762719103987365, "children": { "UnityEnvironment._generate_step_input": { "total": 5.488069929013079, "count": 18222, "is_parallel": true, "self": 5.488069929013079 }, "communicator.exchange": { "total": 203.49157033100516, "count": 18222, "is_parallel": true, "self": 203.49157033100516 }, "steps_from_proto": { "total": 33.4936955390022, "count": 18222, "is_parallel": true, "self": 6.664963676002401, "children": { "_process_rank_one_or_two_observation": { "total": 26.828731862999803, "count": 182220, "is_parallel": true, "self": 26.828731862999803 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012108500004615053, "count": 1, "self": 0.00012108500004615053, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 472.6929357600122, "count": 433665, "is_parallel": true, "self": 10.74746682900809, "children": { "process_trajectory": { "total": 264.02303638700397, "count": 433665, "is_parallel": true, "self": 262.46736175700397, "children": { "RLTrainer._checkpoint": { "total": 1.5556746299999986, "count": 4, "is_parallel": true, "self": 1.5556746299999986 } } }, "_update_policy": { "total": 197.92243254400012, "count": 90, "is_parallel": true, "self": 72.8912490109937, "children": { "TorchPPOOptimizer.update": { "total": 125.03118353300641, "count": 4587, "is_parallel": true, "self": 125.03118353300641 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21771343000000343, "count": 1, "self": 0.001246682999976656, "children": { "RLTrainer._checkpoint": { "total": 0.21646674700002677, "count": 1, "self": 0.21646674700002677 } } } } } } }