Foundations of Reinforcement Learning and Interactive Decision Making
Abstract
The notes present a statistical framework for reinforcement learning using frequentist and Bayesian approaches, focusing on function approximation and flexible models like neural networks, with applications to multi-armed and contextual bandits, structured bandits, and high-dimensional feedback.
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.
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper