State Similarity Based Approach for Improving Performance in RL
Abstract
This paper employs state similarity to improve reinforcement learning performance. This is achieved by first identifying states with similar sub-policies. Then, a tree is constructed to be used for locating common action sequences of states as derived from possible optimal policies. Such sequences are utilized for defining a similarity function between states, which is essential for reflecting updates on the action-value function of a state onto all similar states. As a result, the experience acquired during learning can be applied to a broader context. Effectiveness of the method is demonstrated empirically.
Cite
Text
Girgin et al. "State Similarity Based Approach for Improving Performance in RL." International Joint Conference on Artificial Intelligence, 2007.Markdown
[Girgin et al. "State Similarity Based Approach for Improving Performance in RL." International Joint Conference on Artificial Intelligence, 2007.](https://mlanthology.org/ijcai/2007/girgin2007ijcai-state/)BibTeX
@inproceedings{girgin2007ijcai-state,
title = {{State Similarity Based Approach for Improving Performance in RL}},
author = {Girgin, Sertan and Polat, Faruk and Alhajj, Reda},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2007},
pages = {817-822},
url = {https://mlanthology.org/ijcai/2007/girgin2007ijcai-state/}
}