SCIENCE@home

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

Alane Suhr,Yoav Artzi

Published 2018 in Annual Meeting of the Association for Computational Linguistics

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.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-41 of 41 references · Page 1 of 1

CITED BY

Showing 1-33 of 33 citing papers · Page 1 of 1