Stable Fitted Reinforcement Learning

Abstract

We describe the reinforcement learning problem, motivate algo(cid:173) rithms which seek an approximation to the Q function, and present new convergence results for two such algorithms.

Cite

Text

Gordon. "Stable Fitted Reinforcement Learning." Neural Information Processing Systems, 1995.

Markdown

[Gordon. "Stable Fitted Reinforcement Learning." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/gordon1995neurips-stable/)

BibTeX

@inproceedings{gordon1995neurips-stable,
  title     = {{Stable Fitted Reinforcement Learning}},
  author    = {Gordon, Geoffrey J.},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {1052-1058},
  url       = {https://mlanthology.org/neurips/1995/gordon1995neurips-stable/}
}