Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces are quite common in real-wor...
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a mo...
We address the problem of autonomously learning controllers for visioncapable mobile robots. We extend McCallum's (1995) Nearest-Sequence Memory algorithm to allow for genera...
Viktor Zhumatiy, Faustino J. Gomez, Marcus Hutter,...
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...
Reinforcement learning is an effective machine learning paradigm in domains represented by compact and discrete state-action spaces. In high-dimensional and continuous domains, ti...