Evolutionary Tile Coding: An Automated State Abstraction Algorithm for Reinforcement Learning

@inproceedings{Lin2010EvolutionaryTC,
  title={Evolutionary Tile Coding: An Automated State Abstraction Algorithm for Reinforcement Learning},
  author={Stephen Lin and Robert Wright},
  booktitle={Abstraction, Reformulation, and Approximation},
  year={2010}
}
Reinforcement learning (RL) algorithms have the ability to learn optimal policies for control problems by exploring a domain’s state space. Unfortunately, for most problems the size of the state space is too great for RL technologies to fully explore in order to find good policies. State abstraction is one way of reducing the size and complexity of a domain’s state space in order to enable RL. In this paper we introduce a new approach for automatically deriving state abstractions called… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS
12 Citations
13 References
Similar Papers

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…