Combining Learned Discrete and Continuous Action Models

8 years 8 months ago
Combining Learned Discrete and Continuous Action Models
Action modeling is an important skill for agents that must perform tasks in novel domains. Previous work on action modeling has focused on learning STRIPS operators in discrete, relational domains. There has also been a separate vein of work in continuous function approximation for use in optimal control in robotics. Most real world domains are grounded in continuous dynamics but also exhibit emergent ties at an abstract relational level of description. These two levels of regularity are often difficult to capture using a single action representation and learning method. In this paper we describe a system that combines discrete and continuous action modeling techniques in the Soar cognitive architecture. Our system accepts a continuous state representation from the environment and derives a relational state on top of it using spatial relations. The dynamics over each representation is learned separately using two simple instance-based algorithms. The predictions from the individual mo...
Joseph Z. Xu, John E. Laird
Added 12 Dec 2011
Updated 12 Dec 2011
Type Journal
Year 2011
Where AAAI
Authors Joseph Z. Xu, John E. Laird
Comments (0)