Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目,它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符
 
 
 
 
 
GitHub 29f82921 [bug-fix] Improve performance for PPO with continuous actions (#3662) 5 年前
..
test_demo_dir Merge pull request #3010 from Unity-Technologies/release-0.12.0-to-master 5 年前
BasicLearning.pb Modified the Basic Environment (#1347) 6 年前
__init__.py check for numpy float64 (#2948) 5 年前
mock_brain.py [bug-fix] Fix issue with more than one continuous actions (#3547) 5 年前
simple_test_envs.py Basic and visual GAIL and BC integration tests (#3626) 5 年前
test.demo Update the test demo (#3466) 5 年前
test_agent_processor.py Clear agent processor properly on episode reset (#3437) 5 年前
test_barracuda_converter.py [tests] Add additional unit tests (#3581) 5 年前
test_bcmodule.py [change] Organize trainer files a bit better (#3538) 5 年前
test_buffer.py Fix clear update buffer when trainer stops training, add test (#3422) 5 年前
test_curriculum.py Allow curricula to be created without files (#3145) 5 年前
test_demo_loader.py Refactor file logic in demo_loader and add unit tests. (#3241) 5 年前
test_distributions.py [bug-fix] Fix entropy computation in MultiCategorialDistribution (#3607) 5 年前
test_ghost.py Merge branch 'master' into develop-splitpolicyoptimizer 5 年前
test_learn.py [change] Clean up trainer interface, clean up GhostTrainer stats (#3634) 5 年前
test_meta_curriculum.py [tests] Visual observation tests (#3549) 5 年前
test_nn_policy.py [tests] Add additional unit tests (#3581) 5 年前
test_policy.py [change] Organize trainer files a bit better (#3538) 5 年前
test_ppo.py [change] Throw a proper error when sequence length is greater than batch size. (#3583) 5 年前
test_reward_signals.py [change] Organize trainer files a bit better (#3538) 5 年前
test_rl_trainer.py [change] Clean up trainer interface, clean up GhostTrainer stats (#3634) 5 年前
test_sac.py [change] Throw a proper error when sequence length is greater than batch size. (#3583) 5 年前
test_sampler_class.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
test_simple_rl.py [bug-fix] Improve performance for PPO with continuous actions (#3662) 5 年前
test_stats.py [change] Clean up trainer interface, clean up GhostTrainer stats (#3634) 5 年前
test_subprocess_env_manager.py [tests] Make subprocess manager test easier (#3651) 5 年前
test_trainer_controller.py Move advance() logic for environment manager out of trainer_controller (#3234) 5 年前
test_trainer_util.py [tests] Add additional unit tests (#3581) 5 年前
test_trajectory.py Replace BrainInfos with BatchedStepResult (#3207) 5 年前
testdcvis.demo Develop remove past action communication (#2913) 5 年前