## State Aggregation by Growing Neural Gas for Reinforcement Learning in Continuous State Spaces

- Michael Baumann, Hans Kleine Büning
- 2011 10th International Conference on Machine…
- 2011

Highly Influenced

@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} }

- Published 2010 in Abstraction, Reformulation, and Approximation

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