论文标题
Supersuit：用于加固学习环境的简单微饰面
SuperSuit: Simple Microwrappers for Reinforcement Learning Environments
论文作者
论文摘要
在加强学习中，包装器普遍用于改变模型和环境之间传递的信息。尽管它们无处不在，但仍未存在所有流行预处理方法的合理实现。这导致不必要的错误，代码效率低下以及浪费的开发人员时间。因此，我们介绍了一个Python库Supersuit，其中包括所有流行的包装器和包装器，可以轻松地将Lambda功能应用于观察/动作/奖励。它与标准的健身房环境规范兼容，以及针对多机构环境的PETTINGZOO规范。该库可通过https://github.com/pettingzoo-team/supersuit获得，并且可以通过PIP安装。
In reinforcement learning, wrappers are universally used to transform the information that passes between a model and an environment. Despite their ubiquity, no library exists with reasonable implementations of all popular preprocessing methods. This leads to unnecessary bugs, code inefficiencies, and wasted developer time. Accordingly we introduce SuperSuit, a Python library that includes all popular wrappers, and wrappers that can easily apply lambda functions to the observations/actions/reward. It's compatible with the standard Gym environment specification, as well as the PettingZoo specification for multi-agent environments. The library is available at https://github.com/PettingZoo-Team/SuperSuit,and can be installed via pip.
