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.
Reinforcement Learning for Mapping Instructions to Actions
S. Branavan,Harr Chen,Luke Zettlemoyer,R. Barzilay
Published 2009 in Annual Meeting of the Association for Computational Linguistics
ABSTRACT
PUBLICATION RECORD
- Publication year
2009
- Venue
Annual Meeting of the Association for Computational Linguistics
- Publication date
2009-08-02
- Fields of study
Computer Science
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
- No claims are published for this paper.
CONCEPTS
- No concepts are published for this paper.
REFERENCES
Showing 1-21 of 21 references · Page 1 of 1