论文标题
学习动态的抽象表示，用于样品有效的增强学习
Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning
论文作者
论文摘要
在许多现实世界中，学习代理需要同时学习问题的抽象和解决方案。但是，大多数此类抽象需要手工设计和完善，以解决不同问题和应用领域。本文提出了一种新颖的自上而下的方法，用于在进行强化学习时构建状态抽象。从状态变量和模拟器开始，它提出了一种与域无关的方法，用于动态地计算基于Q值在抽象状态中的Q值的分散，因为代理人继续进行和学习。对多个领域和问题的广泛经验评估表明，这种方法会自动学习对问题进行精细调整的抽象，产生强大的样本效率，并导致RL代理显着优于现有方法。
In many real-world problems, the learning agent needs to learn a problem's abstractions and solution simultaneously. However, most such abstractions need to be designed and refined by hand for different problems and domains of application. This paper presents a novel top-down approach for constructing state abstractions while carrying out reinforcement learning. Starting with state variables and a simulator, it presents a novel domain-independent approach for dynamically computing an abstraction based on the dispersion of Q-values in abstract states as the agent continues acting and learning. Extensive empirical evaluation on multiple domains and problems shows that this approach automatically learns abstractions that are finely-tuned to the problem, yield powerful sample efficiency, and result in the RL agent significantly outperforming existing approaches.
