{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0605717897415161, "min": 1.0490620136260986, "max": 2.86655855178833, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10138.005859375, "min": 10138.005859375, "max": 29356.42578125, "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": 12.630646705627441, "min": 0.3340834379196167, "max": 12.630646705627441, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2462.97607421875, "min": 64.81218719482422, "max": 2548.0185546875, "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": 0.06710348773519988, "min": 0.06175693350873385, "max": 0.07509611360266503, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2684139509407995, "min": 0.2470277340349354, "max": 0.3754805680133252, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20579815148284622, "min": 0.12338217111833977, "max": 0.2902312720523161, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8231926059313849, "min": 0.49352868447335907, "max": 1.4511563602615805, "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": 24.772727272727273, "min": 3.590909090909091, "max": 24.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1090.0, "min": 158.0, "max": 1355.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.772727272727273, "min": 3.590909090909091, "max": 24.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1090.0, "min": 158.0, "max": 1355.0, "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": "1781737432", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1781738140" }, "total": 708.4176227119997, "count": 1, "self": 0.7897840920004455, "children": { "run_training.setup": { "total": 0.047733720999531215, "count": 1, "self": 0.047733720999531215 }, "TrainerController.start_learning": { "total": 707.5801048989997, "count": 1, "self": 1.0188005810396135, "children": { "TrainerController._reset_env": { "total": 4.77964748300019, "count": 1, "self": 4.77964748300019 }, "TrainerController.advance": { "total": 701.6926403059597, "count": 18202, "self": 0.49046066595838056, "children": { "env_step": { "total": 701.2021796400013, "count": 18202, "self": 554.6772724828597, "children": { "SubprocessEnvManager._take_step": { "total": 146.04294680308067, "count": 18202, "self": 2.39178797211207, "children": { "TorchPolicy.evaluate": { "total": 143.6511588309686, "count": 18202, "self": 143.6511588309686 } } }, "workers": { "total": 0.4819603540609023, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 703.6741299579917, "count": 18202, "is_parallel": true, "self": 294.6786655909709, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008143035999637505, "count": 1, "is_parallel": true, "self": 0.005187791000935249, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029552449987022555, "count": 10, "is_parallel": true, "self": 0.0029552449987022555 } } }, "UnityEnvironment.step": { "total": 0.06055144899983134, "count": 1, "is_parallel": true, "self": 0.0008154400002240436, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004808060002687853, "count": 1, "is_parallel": true, "self": 0.0004808060002687853 }, "communicator.exchange": { "total": 0.05678307399921323, "count": 1, "is_parallel": true, "self": 0.05678307399921323 }, "steps_from_proto": { "total": 0.0024721290001252783, "count": 1, "is_parallel": true, "self": 0.0005716420000680955, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019004870000571827, "count": 10, "is_parallel": true, "self": 0.0019004870000571827 } } } } } } }, "UnityEnvironment.step": { "total": 408.99546436702076, "count": 18201, "is_parallel": true, "self": 19.092830343957758, "children": { "UnityEnvironment._generate_step_input": { "total": 8.996257996996064, "count": 18201, "is_parallel": true, "self": 8.996257996996064 }, "communicator.exchange": { "total": 320.2233037830392, "count": 18201, "is_parallel": true, "self": 320.2233037830392 }, "steps_from_proto": { "total": 60.68307224302771, "count": 18201, "is_parallel": true, "self": 11.919586834099391, "children": { "_process_rank_one_or_two_observation": { "total": 48.76348540892832, "count": 182010, "is_parallel": true, "self": 48.76348540892832 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00023453999983757967, "count": 1, "self": 0.00023453999983757967, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 696.1692025332186, "count": 644338, "is_parallel": true, "self": 15.564965601978656, "children": { "process_trajectory": { "total": 376.9867592512428, "count": 644338, "is_parallel": true, "self": 376.0709509962426, "children": { "RLTrainer._checkpoint": { "total": 0.9158082550002291, "count": 4, "is_parallel": true, "self": 0.9158082550002291 } } }, "_update_policy": { "total": 303.61747767999714, "count": 90, "is_parallel": true, "self": 62.01559714998075, "children": { "TorchPPOOptimizer.update": { "total": 241.6018805300164, "count": 4587, "is_parallel": true, "self": 241.6018805300164 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08878198900038115, "count": 1, "self": 0.0010370190002504387, "children": { "RLTrainer._checkpoint": { "total": 0.0877449700001307, "count": 1, "self": 0.0877449700001307 } } } } } } }