Robust, Efficient, Globally-Optimized Reinforcement Learning with the Parti-Game Algorithm

Abstract

Parti-game (Moore 1994a; Moore 1994b; Moore and Atkeson 1995) is a reinforcement learning (RL) algorithm that has a lot of promise in over(cid:173) coming the curse of dimensionality that can plague RL algorithms when applied to high-dimensional problems. In this paper we introduce mod(cid:173) ifications to the algorithm that further improve its performance and ro(cid:173) bustness. In addition, while parti-game solutions can be improved locally by standard local path-improvement techniques, we introduce an add-on algorithm in the same spirit as parti-game that instead tries to improve solutions in a non-local manner.

Cite

Text

Al-Ansari and Williams. "Robust, Efficient, Globally-Optimized Reinforcement Learning with the Parti-Game Algorithm." Neural Information Processing Systems, 1998.

Markdown

[Al-Ansari and Williams. "Robust, Efficient, Globally-Optimized Reinforcement Learning with the Parti-Game Algorithm." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/alansari1998neurips-robust/)

BibTeX

@inproceedings{alansari1998neurips-robust,
  title     = {{Robust, Efficient, Globally-Optimized Reinforcement Learning with the Parti-Game Algorithm}},
  author    = {Al-Ansari, Mohammad A. and Williams, Ronald J.},
  booktitle = {Neural Information Processing Systems},
  year      = {1998},
  pages     = {961-967},
  url       = {https://mlanthology.org/neurips/1998/alansari1998neurips-robust/}
}