{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9606413841247559, "min": 0.9493950605392456, "max": 2.8656938076019287, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9172.2041015625, "min": 9172.2041015625, "max": 29379.09375, "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": 12.26877498626709, "min": 0.46508121490478516, "max": 12.26877498626709, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2392.4111328125, "min": 90.22575378417969, "max": 2471.877197265625, "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": 0.06731609070009333, "min": 0.06189966031546218, "max": 0.0707998099381025, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2692643628003733, "min": 0.24759864126184872, "max": 0.3517164690077634, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2065445152567882, "min": 0.11406388257255815, "max": 0.2785002820047678, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8261780610271529, "min": 0.4562555302902326, "max": 1.3289356474198548, "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": 24.045454545454547, "min": 3.1818181818181817, "max": 24.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1058.0, "min": 140.0, "max": 1319.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.045454545454547, "min": 3.1818181818181817, "max": 24.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1058.0, "min": 140.0, "max": 1319.0, "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": "1720962997", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720963461" }, "total": 463.99943419300007, "count": 1, "self": 0.44325551699989774, "children": { "run_training.setup": { "total": 0.059548536000079366, "count": 1, "self": 0.059548536000079366 }, "TrainerController.start_learning": { "total": 463.4966301400001, "count": 1, "self": 0.5996067370004994, "children": { "TrainerController._reset_env": { "total": 2.9624280150000004, "count": 1, "self": 2.9624280150000004 }, "TrainerController.advance": { "total": 459.8373970919994, "count": 18201, "self": 0.28879534199177215, "children": { "env_step": { "total": 459.5486017500076, "count": 18201, "self": 299.01227862999326, "children": { "SubprocessEnvManager._take_step": { "total": 160.24741493600652, "count": 18201, "self": 1.5454635260088025, "children": { "TorchPolicy.evaluate": { "total": 158.70195140999772, "count": 18201, "self": 158.70195140999772 } } }, "workers": { "total": 0.28890818400782337, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 462.2791329729955, "count": 18201, "is_parallel": true, "self": 234.44800561898649, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005678326999941419, "count": 1, "is_parallel": true, "self": 0.004110584000159179, "children": { "_process_rank_one_or_two_observation": { "total": 0.00156774299978224, "count": 10, "is_parallel": true, "self": 0.00156774299978224 } } }, "UnityEnvironment.step": { "total": 0.03926194499990743, "count": 1, "is_parallel": true, "self": 0.0006964739998238656, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042919000009078445, "count": 1, "is_parallel": true, "self": 0.00042919000009078445 }, "communicator.exchange": { "total": 0.03606244900004185, "count": 1, "is_parallel": true, "self": 0.03606244900004185 }, "steps_from_proto": { "total": 0.002073831999950926, "count": 1, "is_parallel": true, "self": 0.00040619100002459163, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016676409999263342, "count": 10, "is_parallel": true, "self": 0.0016676409999263342 } } } } } } }, "UnityEnvironment.step": { "total": 227.83112735400903, "count": 18200, "is_parallel": true, "self": 10.356211139018228, "children": { "UnityEnvironment._generate_step_input": { "total": 5.52808312199204, "count": 18200, "is_parallel": true, "self": 5.52808312199204 }, "communicator.exchange": { "total": 177.24732900400988, "count": 18200, "is_parallel": true, "self": 177.24732900400988 }, "steps_from_proto": { "total": 34.699504088988874, "count": 18200, "is_parallel": true, "self": 6.628676653986645, "children": { "_process_rank_one_or_two_observation": { "total": 28.07082743500223, "count": 182000, "is_parallel": true, "self": 28.07082743500223 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014626300003328652, "count": 1, "self": 0.00014626300003328652, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.24385064301214, "count": 660475, "is_parallel": true, "self": 14.668745391023322, "children": { "process_trajectory": { "total": 251.4228497769892, "count": 660475, "is_parallel": true, "self": 250.38599823398908, "children": { "RLTrainer._checkpoint": { "total": 1.0368515430001253, "count": 4, "is_parallel": true, "self": 1.0368515430001253 } } }, "_update_policy": { "total": 188.1522554749996, "count": 90, "is_parallel": true, "self": 59.00047284099605, "children": { "TorchPPOOptimizer.update": { "total": 129.15178263400355, "count": 4584, "is_parallel": true, "self": 129.15178263400355 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09705203300018184, "count": 1, "self": 0.001233088000162752, "children": { "RLTrainer._checkpoint": { "total": 0.09581894500001908, "count": 1, "self": 0.09581894500001908 } } } } } } }