OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Optimal sample selection for batch-mode reinforcement learning

Rachelson, Emmanuel and Schnitzler, François and Wehenkel, Louis and Ernst, Damien Optimal sample selection for batch-mode reinforcement learning. (2011) In: 3rd International Conference on Agents and Artificial Intelligence (ICAART 2011), 28 January 2011 - 30 January 2011 (Rome, Italy).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
869kB
[img] (Document in English)

Plain Text (Author's version)
38kB

Abstract

We introduce the Optimal Sample Selection(OSS) meta-algorithm for solving discrete-time Optimal Control problems. This meta-algorithm maps the problem of finding a near-optimal closed-loop policy to the identification of a small set of one-step system transitions, leading to high-quality policies when used as input of a batch-mode Reinforcement Learning (RL) algorithm. We detail a particular instance of this OSS meta-algorithm that uses tree-based Fitted Q-Iteration as a batch-mode RL algorithm and Cross Entropy search as a method for navigating efficiently in the space of sample sets. The results show that this particular instance of OSS algorithms is able to identify rapidly small sample sets leading to high-quality policies.

Item Type:Conference or Workshop Item (Paper)
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:Other partners > Université de Liège (BELGIUM)
Statistics:download
Deposited On:30 Nov 2017 09:43

Repository Staff Only: item control page