Relational temporal difference learning

Nima Asgharbeygi, David J. Stracuzzi, Pat Langley

Abstract: We introduce relational temporal difference learning as an effective approach to solving multi-agent Markov decision problems with large state spaces. Our algorithm uses temporal difference reinforcement to learn a distributed value function represented over a conceptual hierarchy of relational predicates. We present experiments using two domains from the General Game Playing repository, in which we observe that our system achieves higher learning rates than non-relational methods. We also discuss related work and directions for future research.