Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of deep learning, Deep RL (DRL) has witnessed great success over a wide spectrum of complex control tasks. Despite the encouraging results achieved, the deep neural network-based backbone is widely deemed as a black box that impedes practitioners to trust and employ trained agents in realistic scenarios where high security and reliability are essential. To alleviate this issue, a large volume of literature devoted to shedding light on the inner workings of the intelligent agents has been proposed, by constructing intrinsic interpretability or post-hoc explainability. In this survey, we provide a comprehensive review of existing works on eXplainable RL (XRL) and introduce a new taxonomy where prior works are clearly categorized into model-explaining, reward-explaining, state-explaining, and task-explaining methods. We also review and highlight RL methods that conversely leverage human knowledge to promote learning efficiency and final performance of agents while this kind of method is often ignored in XRL field. Some open challenges and opportunities in XRL are discussed. This survey intends to provide a high-level summarization and better understanding of XRL and to motivate future research on more effective XRL solutions. Corresponding open source codes are collected and categorized at https://github.com/Plankson/awesome-explainable-reinforcement-learning.
翻译:智能剂与环境互动以实现长期目标的流行机器学习模式(RL)是智能剂与环境互动以实现长期目标的流行机器学习模式。在深层次学习的重新抬头的驱动下,Deep RL(DRL)在一系列复杂的控制任务中取得了巨大成功。尽管取得了令人鼓舞的成果,但深神经网络骨干被广泛视为一个黑盒,在高度安全和可靠性至关重要的现实情景下,使从业人员无法信任并雇用训练有素的代理人。为了缓解这一问题,已经提出了大量文献,专门用来揭示智能剂内部工作的信息,通过建立内在的可解释性或事后的可解释性。在这次调查中,我们全面审查了关于可扩展的RL(XRL)的现有工作,并引入了一个新的分类学。以前的工作被明确归类为示范解释、报酬解释、州解释和任务解释方法。我们还审查并突出强调了大量RL方法,这些工具往往在 XRRL 领域被忽略,从而可以更好地利用人类知识来提高代理者的学习效率和最终表现。一些公开的方法,在XRRL领域被忽略。一些公开的挑战和新分类的分类研究中,在X-crealalalalal-calal-al-alisalisalalalalalalalaldealalalalalalisalisal to toal to sual to sual toal toal toalalalalal to subal to sualalalalal to subal to subal toal to subal subal toal toal toal to laxxxxxxaltialtial toal laxxxxxxxxal laxxxxxxxxxxxxxxxxxxxxxxxxxalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalaldalalalalalalalalalalalalalalalaldalalalalalalal