In this paper, we present a reinforcement learning approach for mapping natural language instructions to sequences of executable actions. We assume access to a reward function tha...
S. R. K. Branavan, Harr Chen, Luke S. Zettlemoyer,...
The advent of emerging technologies such as Web services, serviceoriented architecture, and cloud computing has enabled us to perform business services more efficiently and effec...
As an alternative to planning, an approach to highlevel agent control based on concurrent program execution is considered. A formal definition in the situation calculus of such a ...
In this paper we present an agent language that combines agent functionality with an action theory and model-theoretic semantics. The language is based on abductive logic programmi...
Weare concerned with the implications and interactions of three commonexpressive extensions to classical planning: conditional plans, context-dependent actions, and nondeterminist...