Corpus ID: 202770731

On the Utility of Learning about Humans for Human-AI Coordination

@inproceedings{Carroll2019OnTU,
  title={On the Utility of Learning about Humans for Human-AI Coordination},
  author={Micah Carroll and Rohin Shah and M. Ho and T. Griffiths and S. Seshia and P. Abbeel and A. Dragan},
  booktitle={NeurIPS},
  year={2019}
}

Micah Carroll, Rohin Shah, +4 authors A. Dragan

Published in NeurIPS 2019

Computer Science, Mathematics

While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can converge to coordination protocols that fail to understand and be understood by humans. To demonstrate this, we introduce a simple environment that requires challenging coordination, based on the popular game Overcooked, and learn a simple model that… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed