Stable Fitted Reinforcement Learning

@inproceedings{Gordon1995StableFR,
  title={Stable Fitted Reinforcement Learning},
  author={Geoffrey J. Gordon},
  booktitle={NIPS},
  year={1995}
}
We describe the reinforcement learning problem, motivate algorithms which seek an approximation to the Q function, and present new convergence results for two such algorithms. 
Highly Cited
This paper has 48 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Similar Papers

Loading similar papers…