{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.007237195968628, "min": 1.007237195968628, "max": 2.8464362621307373, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9705.7373046875, "min": 9705.7373046875, "max": 29119.04296875, "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": 12.68714427947998, "min": 0.4845066964626312, "max": 12.68714427947998, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2473.9931640625, "min": 93.99430084228516, "max": 2544.46337890625, "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": 0.0707859765478169, "min": 0.06170841392047484, "max": 0.07401954414797765, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2831439061912676, "min": 0.24683365568189936, "max": 0.3700977207398882, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21859922873623233, "min": 0.16195449212511234, "max": 0.2942085621111533, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8743969149449293, "min": 0.6478179685004494, "max": 1.4278153234398832, "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": 25.522727272727273, "min": 3.977272727272727, "max": 25.522727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 175.0, "max": 1353.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 3.977272727272727, "max": 25.522727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 175.0, "max": 1353.0, "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": "1710107034", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710107482" }, "total": 448.103487955, "count": 1, "self": 0.7431714040000088, "children": { "run_training.setup": { "total": 0.05723550199991223, "count": 1, "self": 0.05723550199991223 }, "TrainerController.start_learning": { "total": 447.30308104900007, "count": 1, "self": 0.5895444559986345, "children": { "TrainerController._reset_env": { "total": 3.4203255969999873, "count": 1, "self": 3.4203255969999873 }, "TrainerController.advance": { "total": 443.15946794400145, "count": 18221, "self": 0.26305173199773435, "children": { "env_step": { "total": 442.8964162120037, "count": 18221, "self": 286.07757298699266, "children": { "SubprocessEnvManager._take_step": { "total": 156.54081555400774, "count": 18221, "self": 1.427922445006402, "children": { "TorchPolicy.evaluate": { "total": 155.11289310900133, "count": 18221, "self": 155.11289310900133 } } }, "workers": { "total": 0.27802767100331494, "count": 18221, "self": 0.0, "children": { "worker_root": { "total": 446.063348920007, "count": 18221, "is_parallel": true, "self": 222.40511389900564, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007432954000023528, "count": 1, "is_parallel": true, "self": 0.00575043100025141, "children": { "_process_rank_one_or_two_observation": { "total": 0.001682522999772118, "count": 10, "is_parallel": true, "self": 0.001682522999772118 } } }, "UnityEnvironment.step": { "total": 0.03569266699992113, "count": 1, "is_parallel": true, "self": 0.0006857739998622492, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038467299998501403, "count": 1, "is_parallel": true, "self": 0.00038467299998501403 }, "communicator.exchange": { "total": 0.032631860000037705, "count": 1, "is_parallel": true, "self": 0.032631860000037705 }, "steps_from_proto": { "total": 0.001990360000036162, "count": 1, "is_parallel": true, "self": 0.0004039089998286727, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015864510002074894, "count": 10, "is_parallel": true, "self": 0.0015864510002074894 } } } } } } }, "UnityEnvironment.step": { "total": 223.65823502100136, "count": 18220, "is_parallel": true, "self": 10.364479193011334, "children": { "UnityEnvironment._generate_step_input": { "total": 5.324780425006111, "count": 18220, "is_parallel": true, "self": 5.324780425006111 }, "communicator.exchange": { "total": 174.23928861598313, "count": 18220, "is_parallel": true, "self": 174.23928861598313 }, "steps_from_proto": { "total": 33.72968678700079, "count": 18220, "is_parallel": true, "self": 6.426458101006574, "children": { "_process_rank_one_or_two_observation": { "total": 27.303228685994213, "count": 182200, "is_parallel": true, "self": 27.303228685994213 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017507999996269064, "count": 1, "self": 0.00017507999996269064, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 437.7873389239876, "count": 673028, "is_parallel": true, "self": 14.643829242038805, "children": { "process_trajectory": { "total": 242.06746022794857, "count": 673028, "is_parallel": true, "self": 240.50640663794854, "children": { "RLTrainer._checkpoint": { "total": 1.5610535900000286, "count": 4, "is_parallel": true, "self": 1.5610535900000286 } } }, "_update_policy": { "total": 181.0760494540002, "count": 90, "is_parallel": true, "self": 51.586602490998644, "children": { "TorchPPOOptimizer.update": { "total": 129.48944696300157, "count": 4584, "is_parallel": true, "self": 129.48944696300157 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13356797200003712, "count": 1, "self": 0.0012841030002164189, "children": { "RLTrainer._checkpoint": { "total": 0.1322838689998207, "count": 1, "self": 0.1322838689998207 } } } } } } }