@inproceedings{d6baec8fee7c45ac8e1d3b18e9425154,
title = "Reducing sample complexity in reinforcement learning by transferring transition and reward probabilities",
abstract = "Most existing reinforcement learning algorithms require many trials until they obtain optimal policies. In this study, we apply transfer learning to reinforcement learning to realize greater efficiency. We propose a new algorithm called TR-MAX, based on the R-MAX algorithm. TR-MAX transfers the transition and reward probabilities from a source task to a target task as prior knowledge. We theoretically analyze the sample complexity of TR-MAX. Moreover, we show that TR-MAX performs much better in practice than R-MAX in maze tasks.",
keywords = "PAC-MDP, Reinforcement learning, Sample complexity, Transfer learning",
author = "Kouta Oguni and Kazuyuki Narisawa and Ayumi Shinohara",
year = "2014",
doi = "10.5220/0004915606320638",
language = "English",
isbn = "9789897580154",
series = "ICAART 2014 - Proceedings of the 6th International Conference on Agents and Artificial Intelligence",
publisher = "SciTePress",
pages = "632--638",
booktitle = "ICAART 2014 - Proceedings of the 6th International Conference on Agents and Artificial Intelligence",
note = "6th International Conference on Agents and Artificial Intelligence, ICAART 2014 ; Conference date: 06-03-2014 Through 08-03-2014",
}