Monte Carlo and Temporal Difference Methods in Reinforcement Learning [AI-eXplained]

Isaac Han, Seungwon Oh, Hoyoun Jung, Insik Chung, Kyung-Joong Kim

Abstract: Reinforcement learning (RL) is a subset of machine learning that allows intelligent agents to acquire the ability of executing desired actions through interactions with an environment. Its remarkable progress has achieved significant results in diverse domains, such as Go and StarCraft, and practical challenges like protein-folding. This short paper presents overviews of two common RL approaches: the Monte Carlo and temporal difference methods. To obtain a more comprehensive understanding of these concepts and gain practical experience, readers can access the full article on IEEE Xplore, which includes interactive materials and examples.