Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation.
2018
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.
- Correction
- Cite
- Save
- Machine Reading By IdeaReader
0
References
2
Citations
NaN
KQI