Relational Reinforcement Learning in Infinite Mario

Shiwali Mohan; John E. Laird

Relational Reinforcement Learning in Infinite Mario

Artificial Intelligence 2012-03-01 v1

Authors: Shiwali Mohan , John E. Laird

Abstract

Relational representations in reinforcement learning allow for the use of structural information like the presence of objects and relationships between them in the description of value functions. Through this paper, we show that such representations allow for the inclusion of background knowledge that qualitatively describes a state and can be used to design agents that demonstrate learning behavior in domains with large state and actions spaces such as computer games.

Keywords

representation learning reinforcement learning multi-agent reinforcement learning

Cite

@article{arxiv.1202.6386,
  title  = {Relational Reinforcement Learning in Infinite Mario},
  author = {Shiwali Mohan and John E. Laird},
  journal= {arXiv preprint arXiv:1202.6386},
  year   = {2012}
}

Related papers

View all related →