Speeding up Tabular Reinforcement Learning Using State-Action Similarities
Ariel Rosenfeld, Mattew E. Taylor and Sarit Kraus; Speeding up Tabular Reinforcement Learning Using State-Action Similarities (Exteded Abstract). AAMAS 2017. [26% acceptance rate, additional 21% for extended abstracts] - Best Paper Award for the extended version at the Fifteenth Adaptive Learning Agents workshop at AAMAS 2017 [40% acceptance rate].
One of the most prominent approaches for speeding up reinforcement learning is injecting human prior knowledge into the learning
agent. This paper proposes a novel method to speed up temporal
difference learning by using state-action similarities. These handcoded similarities are tested in three well-studied domains of varying complexity, demonstrating our approach’s benefits.