Reinforcement Learning for Mapping Instructions to Actions

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 that defines the quality of the executed actions. During training, the learner repeatedly constructs action sequences for a set of documents, executes those actions, and observes the resulting reward. We use a policy gradient algorithm to estimate the parameters of a log-linear model for action selection. We apply our method to interpret instructions in two domains -- Windows troubleshooting guides and game tutorials. Our results demonstrate that this method can rival supervised learning techniques while requiring few or no annotated training examples.1

• Type: Journal
• Year: 2009
• Where: ACL
• Authors: S. R. K. Branavan, Harr Chen, Luke S. Zettlemoyer, Regina Barzilay
• Keywords: ACL 2009, Computational Linguistics, Executable Actions, Natural Language Instructions, Reward Function