Sciweavers

Share
ABIALS
2008
Springer

Multiscale Anticipatory Behavior by Hierarchical Reinforcement Learning

9 years 1 months ago
Multiscale Anticipatory Behavior by Hierarchical Reinforcement Learning
Abstract. In order to establish autonomous behavior for technical systems, the well known trade-off between reactive control and deliberative planning has to be considered. Within this paper, we combine both principles by proposing a two-level hierarchical reinforcement learning scheme to enable the system to autonomously determine suitable solutions to new tasks. The approach is based on a behavior representation specified by hybrid automata, which combines continuous and discrete behavior, to predict (anticipate) the outcome of a sequence of actions. igher layer of the hierarchical scheme, the behavior is abstracted in the form of finite state automata, on which value function iteration is performed to obtain a goal leading sequence of subtasks. This sequence is realized on the lower layer by applying policy gradient-based reinforcement learning to the hybrid automaton model. The iteration between both layers leads to a consistent and goal-attaining behavior, as shown for a simple ro...
Matthias Rungger, Hao Ding, Olaf Stursberg
Added 12 Oct 2010
Updated 12 Oct 2010
Type Conference
Year 2008
Where ABIALS
Authors Matthias Rungger, Hao Ding, Olaf Stursberg
Comments (0)
books