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...
Reinforcement learning addresses the problem of learning to select actions in order to maximize one's performance inunknownenvironments. Toscale reinforcement learning to com...
Abstract— Continuous action sets are used in many reinforcement learning (RL) applications in robot control since the control input is continuous. However, discrete action sets a...
Akihiko Yamaguchi, Jun Takamatsu, Tsukasa Ogasawar...
Learning in real-world domains often requires to deal with continuous state and action spaces. Although many solutions have been proposed to apply Reinforcement Learning algorithm...
Alessandro Lazaric, Marcello Restelli, Andrea Bona...
We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This ...