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,...
Abstract. Failures are unavoidable in many circumstances. For example, an agent may fail at some point to perform a task in a dynamic environment. Robust systems typically have mec...
— Neural networks have been proposed as an ideal cognitive modeling methodology to deal with the symbol grounding problem. More recently, such neural network approaches have been...
The behavior of an agent is defined through the specification of plans and actions. Agents have a set of plans that are selected to be executed according to their goals (and other...
Viviane Torres da Silva, Ricardo Choren, Carlos Jo...
We present an algorithm that derives actions' effects and preconditions in partially observable, relational domains. Our algorithm has two unique features: an expressive rela...