English

Training an Interactive Helper

Artificial Intelligence 2019-07-03 v2 Machine Learning Multiagent Systems

Abstract

Developing agents that can quickly adapt their behavior to new tasks remains a challenge. Meta-learning has been applied to this problem, but previous methods require either specifying a reward function which can be tedious or providing demonstrations which can be inefficient. In this paper, we investigate if, and how, a "helper" agent can be trained to interactively adapt their behavior to maximize the reward of another agent, whom we call the "prime" agent, without observing their reward or receiving explicit demonstrations. To this end, we propose to meta-learn a helper agent along with a prime agent, who, during training, observes the reward function and serves as a surrogate for a human prime. We introduce a distribution of multi-agent cooperative foraging tasks, in which only the prime agent knows the objects that should be collected. We demonstrate that, from the emerged physical communication, the trained helper rapidly infers and collects the correct objects.

Keywords

Cite

@article{arxiv.1906.10165,
  title  = {Training an Interactive Helper},
  author = {Mark Woodward and Chelsea Finn and Karol Hausman},
  journal= {arXiv preprint arXiv:1906.10165},
  year   = {2019}
}

Comments

The paper "Learning to Interactively Learn and Assist" (LILA), at arXiv:1906.10187, supersedes this paper. This preliminary workshop paper appeared in the Emergent Communication Workshop and Workshop on Learning by Instruction at NeurIPS 2018

R2 v1 2026-06-23T10:02:20.753Z