# Training an Interactive Helper

## TL;DR

This paper introduces a meta-learning approach to train a helper agent that interactively adapts to assist a prime agent in cooperative tasks without explicit demonstrations or reward observations, enabling rapid and effective collaboration.

## Contribution

It proposes a novel meta-learning framework for training helper agents that learn to assist prime agents through physical communication in cooperative tasks.

## Key findings

- Helper agents rapidly infer correct objects to collect.
- Physical communication emerges as a key to cooperation.
- Helper agents adapt quickly without explicit reward signals.

## 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.