Training an Interactive Helper
This addresses the challenge of creating interactive helpers for tasks like human-AI collaboration, but it is incremental as it builds on meta-learning with a specific multi-agent setup.
The paper tackles the problem of training an agent to adaptively assist another agent without observing rewards or demonstrations, by meta-learning both agents in cooperative foraging tasks, and shows the helper quickly infers and collects correct objects from physical communication.
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.