@inproceedings{45e5c3d7c3c0473db41410b88b1f01e4,
title = "An intrinsic reward mechanism for efficient exploration",
abstract = "How should a reinforcement learning agent act if its sole purpose is to efficiently learn an optimal policy for later use? In other words, how should it explore, to be able to exploit later? We formulate this problem as a Markov Decision Process by explicitly modeling the internal state of the agent and propose a principled heuristic for its solution. We present experimental results in a number of domains, also exploring the algorithm{\textquoteright}s use for learning a policy for a skill given its reward function{\textemdash}an important but neglected component of skill discovery.",
author = "{\"O}zg{\"u}r {\c S}im{\c s}ek and Barto, \{Andrew G.\}",
year = "2006",
month = jun,
day = "25",
doi = "10.1145/1143844.1143949",
language = "English",
volume = "148",
series = "ACM International Conference Proceedings",
publisher = "Association for Computing Machinery",
pages = "833--840",
editor = "Cohen, \{William W.\} and Andrew Moore",
booktitle = "Proceedings of the Twenty-Third International Conference on Machine Learning (ICML 2006): Pittsburgh, Pennsylvania, USA, June 25-29, 2006",
address = "USA United States",
}