Foundations of Reinforcement Learning and Interactive Decision Making
This work offers foundational insights for researchers and practitioners in machine learning, but it is incremental as it synthesizes existing perspectives rather than introducing new breakthroughs.
The lecture notes provide a statistical perspective on reinforcement learning and interactive decision making, presenting a unifying framework for the exploration-exploitation dilemma using frequentist and Bayesian approaches, with connections to supervised learning and a focus on function approximation and neural networks.
These lecture notes give a statistical perspective on the foundations of reinforcement learning and interactive decision making. We present a unifying framework for addressing the exploration-exploitation dilemma using frequentist and Bayesian approaches, with connections and parallels between supervised learning/estimation and decision making as an overarching theme. Special attention is paid to function approximation and flexible model classes such as neural networks. Topics covered include multi-armed and contextual bandits, structured bandits, and reinforcement learning with high-dimensional feedback.