Relative Entropy Policy Search

Jan Peters, Katharina Mülling, Yasemin Altun

AAAI 2010 pp. 1607-1612

doi:10.1609/AAAI.V24I1.7727 /aaai/2010/peters2010aaai-relative/

Abstract

Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature convergence and implausible solutions. As first suggested in the context of covariant policy gradients, many of these problems may be addressed by constraining the information loss. In this paper, we continue this path of reasoning and suggest the Relative Entropy Policy Search (REPS) method. The resulting method differs significantly from previous policy gradient approaches and yields an exact update step. It can be shown to work well on typical reinforcement learning benchmark problems.

PDF AAAI Semantic Scholar

Cite

Text

Peters et al. "Relative Entropy Policy Search." AAAI Conference on Artificial Intelligence, 2010. doi:10.1609/AAAI.V24I1.7727

Markdown

[Peters et al. "Relative Entropy Policy Search." AAAI Conference on Artificial Intelligence, 2010.](https://mlanthology.org/aaai/2010/peters2010aaai-relative/) doi:10.1609/AAAI.V24I1.7727

BibTeX

@inproceedings{peters2010aaai-relative,
  title     = {{Relative Entropy Policy Search}},
  author    = {Peters, Jan and Mülling, Katharina and Altun, Yasemin},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2010},
  pages     = {1607-1612},
  doi       = {10.1609/AAAI.V24I1.7727},
  url       = {https://mlanthology.org/aaai/2010/peters2010aaai-relative/}
}