{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0425790548324585, "min": 1.0425790548324585, "max": 2.875286340713501, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9966.0126953125, "min": 9966.0126953125, "max": 29445.806640625, "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": 12.95557689666748, "min": 0.45815733075141907, "max": 13.00505542755127, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.33740234375, "min": 88.88252258300781, "max": 2653.03125, "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": 0.07454958048080752, "min": 0.06108118608858158, "max": 0.07469856861180411, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2981983219232301, "min": 0.24432474435432633, "max": 0.3734928430590206, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19457172237190545, "min": 0.1082585482063758, "max": 0.2930738826008404, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7782868894876218, "min": 0.4330341928255032, "max": 1.4653694130042019, "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": 25.75, "min": 2.8863636363636362, "max": 25.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 127.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 2.8863636363636362, "max": 25.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 127.0, "max": 1394.0, "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": "1696548793", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696549276" }, "total": 482.8226065079999, "count": 1, "self": 0.42594539699985035, "children": { "run_training.setup": { "total": 0.046414790999989464, "count": 1, "self": 0.046414790999989464 }, "TrainerController.start_learning": { "total": 482.35024632000005, "count": 1, "self": 0.5535539560027019, "children": { "TrainerController._reset_env": { "total": 8.148011182999994, "count": 1, "self": 8.148011182999994 }, "TrainerController.advance": { "total": 473.56131912899724, "count": 18202, "self": 0.2614662259994702, "children": { "env_step": { "total": 473.29985290299777, "count": 18202, "self": 322.25550179400153, "children": { "SubprocessEnvManager._take_step": { "total": 150.76902020399575, "count": 18202, "self": 1.4699213059975875, "children": { "TorchPolicy.evaluate": { "total": 149.29909889799816, "count": 18202, "self": 149.29909889799816 } } }, "workers": { "total": 0.2753309050004873, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 481.0928658260041, "count": 18202, "is_parallel": true, "self": 238.47968260000192, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030961969999907524, "count": 1, "is_parallel": true, "self": 0.0007035349999853224, "children": { "_process_rank_one_or_two_observation": { "total": 0.00239266200000543, "count": 10, "is_parallel": true, "self": 0.00239266200000543 } } }, "UnityEnvironment.step": { "total": 0.03443210600002544, "count": 1, "is_parallel": true, "self": 0.0006577039999910994, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033776300000454285, "count": 1, "is_parallel": true, "self": 0.00033776300000454285 }, "communicator.exchange": { "total": 0.03113665000000765, "count": 1, "is_parallel": true, "self": 0.03113665000000765 }, "steps_from_proto": { "total": 0.0022999890000221512, "count": 1, "is_parallel": true, "self": 0.00042016099996544654, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018798280000567047, "count": 10, "is_parallel": true, "self": 0.0018798280000567047 } } } } } } }, "UnityEnvironment.step": { "total": 242.61318322600215, "count": 18201, "is_parallel": true, "self": 10.455187075996918, "children": { "UnityEnvironment._generate_step_input": { "total": 5.309156250999564, "count": 18201, "is_parallel": true, "self": 5.309156250999564 }, "communicator.exchange": { "total": 190.1457339589993, "count": 18201, "is_parallel": true, "self": 190.1457339589993 }, "steps_from_proto": { "total": 36.70310594000637, "count": 18201, "is_parallel": true, "self": 6.738092655994933, "children": { "_process_rank_one_or_two_observation": { "total": 29.965013284011434, "count": 182010, "is_parallel": true, "self": 29.965013284011434 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014601300006233942, "count": 1, "self": 0.00014601300006233942, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 469.7412435299701, "count": 486529, "is_parallel": true, "self": 10.27253238395133, "children": { "process_trajectory": { "total": 259.24122484301864, "count": 486529, "is_parallel": true, "self": 258.1219608540187, "children": { "RLTrainer._checkpoint": { "total": 1.1192639889999327, "count": 4, "is_parallel": true, "self": 1.1192639889999327 } } }, "_update_policy": { "total": 200.22748630300015, "count": 90, "is_parallel": true, "self": 74.43330265300278, "children": { "TorchPPOOptimizer.update": { "total": 125.79418364999736, "count": 4587, "is_parallel": true, "self": 125.79418364999736 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08721603900005448, "count": 1, "self": 0.0008276890000615822, "children": { "RLTrainer._checkpoint": { "total": 0.0863883499999929, "count": 1, "self": 0.0863883499999929 } } } } } } }