English

Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation

Computation and Language 2018-06-12 v2

Abstract

We propose a learning approach for mapping context-dependent sequential instructions to actions. We address the problem of discourse and state dependencies with an attention-based model that considers both the history of the interaction and the state of the world. To train from start and goal states without access to demonstrations, we propose SESTRA, a learning algorithm that takes advantage of single-step reward observations and immediate expected reward maximization. We evaluate on the SCONE domains, and show absolute accuracy improvements of 9.8%-25.3% across the domains over approaches that use high-level logical representations.

Keywords

Cite

@article{arxiv.1805.10209,
  title  = {Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation},
  author = {Alane Suhr and Yoav Artzi},
  journal= {arXiv preprint arXiv:1805.10209},
  year   = {2018}
}

Comments

ACL 2018 Long Paper