{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0132485628128052, "min": 0.9968019127845764, "max": 2.8671085834503174, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9674.4970703125, "min": 9674.4970703125, "max": 29551.2890625, "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": 12.79834270477295, "min": 0.2821919918060303, "max": 12.79834270477295, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2495.6767578125, "min": 54.74524688720703, "max": 2581.87255859375, "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": 0.06663498514692537, "min": 0.05986251443505799, "max": 0.07093851768144055, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2665399405877015, "min": 0.23945005774023195, "max": 0.35469258840720275, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20877301656440192, "min": 0.12385145530981176, "max": 0.28449741307938214, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8350920662576077, "min": 0.49540582123924704, "max": 1.4224870653969108, "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": 25.227272727272727, "min": 3.6136363636363638, "max": 25.318181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 159.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.6136363636363638, "max": 25.318181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 159.0, "max": 1388.0, "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": "1721254391", "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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721254884" }, "total": 493.79026573400006, "count": 1, "self": 0.4835471329997745, "children": { "run_training.setup": { "total": 0.07615750600007232, "count": 1, "self": 0.07615750600007232 }, "TrainerController.start_learning": { "total": 493.2305610950002, "count": 1, "self": 0.6076555339814149, "children": { "TrainerController._reset_env": { "total": 3.673687746000269, "count": 1, "self": 3.673687746000269 }, "TrainerController.advance": { "total": 488.8520875200188, "count": 18201, "self": 0.27456838601619893, "children": { "env_step": { "total": 488.5775191340026, "count": 18201, "self": 320.78350292401547, "children": { "SubprocessEnvManager._take_step": { "total": 167.5020040689683, "count": 18201, "self": 1.590109006988314, "children": { "TorchPolicy.evaluate": { "total": 165.91189506197998, "count": 18201, "self": 165.91189506197998 } } }, "workers": { "total": 0.29201214101885853, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 491.8789529740311, "count": 18201, "is_parallel": true, "self": 249.37494049208362, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005700416999843583, "count": 1, "is_parallel": true, "self": 0.003986337998867384, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017140790009761986, "count": 10, "is_parallel": true, "self": 0.0017140790009761986 } } }, "UnityEnvironment.step": { "total": 0.03775518199972794, "count": 1, "is_parallel": true, "self": 0.0007347849996222067, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039823699989938177, "count": 1, "is_parallel": true, "self": 0.00039823699989938177 }, "communicator.exchange": { "total": 0.034705603000020346, "count": 1, "is_parallel": true, "self": 0.034705603000020346 }, "steps_from_proto": { "total": 0.0019165570001860033, "count": 1, "is_parallel": true, "self": 0.0003618319997258368, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015547250004601665, "count": 10, "is_parallel": true, "self": 0.0015547250004601665 } } } } } } }, "UnityEnvironment.step": { "total": 242.50401248194748, "count": 18200, "is_parallel": true, "self": 11.024339627943391, "children": { "UnityEnvironment._generate_step_input": { "total": 5.67179658095165, "count": 18200, "is_parallel": true, "self": 5.67179658095165 }, "communicator.exchange": { "total": 189.8656773999969, "count": 18200, "is_parallel": true, "self": 189.8656773999969 }, "steps_from_proto": { "total": 35.94219887305553, "count": 18200, "is_parallel": true, "self": 6.986027537078826, "children": { "_process_rank_one_or_two_observation": { "total": 28.956171335976705, "count": 182000, "is_parallel": true, "self": 28.956171335976705 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001260879998881137, "count": 1, "self": 0.0001260879998881137, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 482.76883397291704, "count": 685647, "is_parallel": true, "self": 15.44845173886597, "children": { "process_trajectory": { "total": 264.01752426805524, "count": 685647, "is_parallel": true, "self": 263.0258320850553, "children": { "RLTrainer._checkpoint": { "total": 0.991692182999941, "count": 4, "is_parallel": true, "self": 0.991692182999941 } } }, "_update_policy": { "total": 203.30285796599583, "count": 90, "is_parallel": true, "self": 70.59401997599434, "children": { "TorchPPOOptimizer.update": { "total": 132.70883799000148, "count": 4584, "is_parallel": true, "self": 132.70883799000148 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09700420699982715, "count": 1, "self": 0.0009972759999072878, "children": { "RLTrainer._checkpoint": { "total": 0.09600693099991986, "count": 1, "self": 0.09600693099991986 } } } } } } }