{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9601929187774658, "min": 0.9293788075447083, "max": 2.865156650543213, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9178.484375, "min": 8996.38671875, "max": 29405.103515625, "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": 13.019947052001953, "min": 0.4439733326435089, "max": 13.019947052001953, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2538.8896484375, "min": 86.13082885742188, "max": 2642.269287109375, "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": 0.06748316243265792, "min": 0.06072048079559132, "max": 0.07510441249263856, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2699326497306317, "min": 0.2428819231823653, "max": 0.3755220624631928, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1977607104562077, "min": 0.14859912557842428, "max": 0.2768229871403938, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7910428418248308, "min": 0.5943965023136971, "max": 1.3190029304401547, "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": 26.0, "min": 3.8181818181818183, "max": 26.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1144.0, "min": 168.0, "max": 1416.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.0, "min": 3.8181818181818183, "max": 26.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1144.0, "min": 168.0, "max": 1416.0, "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": "1726681034", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726681604" }, "total": 569.3787852769999, "count": 1, "self": 0.532226888999844, "children": { "run_training.setup": { "total": 0.07123304399999597, "count": 1, "self": 0.07123304399999597 }, "TrainerController.start_learning": { "total": 568.7753253440001, "count": 1, "self": 0.7810082500028557, "children": { "TrainerController._reset_env": { "total": 2.7396840629999986, "count": 1, "self": 2.7396840629999986 }, "TrainerController.advance": { "total": 565.1708084619974, "count": 18202, "self": 0.41212415499751387, "children": { "env_step": { "total": 564.7586843069998, "count": 18202, "self": 437.75925164599806, "children": { "SubprocessEnvManager._take_step": { "total": 126.60287336800278, "count": 18202, "self": 2.234136305995918, "children": { "TorchPolicy.evaluate": { "total": 124.36873706200686, "count": 18202, "self": 124.36873706200686 } } }, "workers": { "total": 0.39655929299900095, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 567.0473123499957, "count": 18202, "is_parallel": true, "self": 264.7216300249958, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002451855999993313, "count": 1, "is_parallel": true, "self": 0.000748377999997274, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017034779999960392, "count": 10, "is_parallel": true, "self": 0.0017034779999960392 } } }, "UnityEnvironment.step": { "total": 0.047471295999997665, "count": 1, "is_parallel": true, "self": 0.0015871759999868118, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008176219999995737, "count": 1, "is_parallel": true, "self": 0.0008176219999995737 }, "communicator.exchange": { "total": 0.0424702580000087, "count": 1, "is_parallel": true, "self": 0.0424702580000087 }, "steps_from_proto": { "total": 0.002596240000002581, "count": 1, "is_parallel": true, "self": 0.0004561880000437668, "children": { "_process_rank_one_or_two_observation": { "total": 0.002140051999958814, "count": 10, "is_parallel": true, "self": 0.002140051999958814 } } } } } } }, "UnityEnvironment.step": { "total": 302.32568232499983, "count": 18201, "is_parallel": true, "self": 14.402551133006853, "children": { "UnityEnvironment._generate_step_input": { "total": 7.218015687996058, "count": 18201, "is_parallel": true, "self": 7.218015687996058 }, "communicator.exchange": { "total": 237.13283684899682, "count": 18201, "is_parallel": true, "self": 237.13283684899682 }, "steps_from_proto": { "total": 43.572278655000076, "count": 18201, "is_parallel": true, "self": 8.57165745800387, "children": { "_process_rank_one_or_two_observation": { "total": 35.00062119699621, "count": 182010, "is_parallel": true, "self": 35.00062119699621 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014049099991098046, "count": 1, "self": 0.00014049099991098046, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 558.6709026139988, "count": 758551, "is_parallel": true, "self": 16.79754296797512, "children": { "process_trajectory": { "total": 300.3555092720238, "count": 758551, "is_parallel": true, "self": 299.38118077902385, "children": { "RLTrainer._checkpoint": { "total": 0.9743284929999732, "count": 4, "is_parallel": true, "self": 0.9743284929999732 } } }, "_update_policy": { "total": 241.51785037399986, "count": 90, "is_parallel": true, "self": 70.96825090099907, "children": { "TorchPPOOptimizer.update": { "total": 170.5495994730008, "count": 4587, "is_parallel": true, "self": 170.5495994730008 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08368407799991928, "count": 1, "self": 0.0013911080000070797, "children": { "RLTrainer._checkpoint": { "total": 0.0822929699999122, "count": 1, "self": 0.0822929699999122 } } } } } } }