Skip to main content

Leveraging Social Networks to Motivate Humans to Train Agents

Guangliang Li‚ Hayley Hung‚ Shimon Whiteson and W. Bradley Knox


Learning from rewards generated by a human trainer observing the agent in action has been demonstrated to be an effective method for humans to teach an agent to perform challenging tasks. However, how to make the agent learn most efficiently from these kinds of human reward is still under-addressed. In this paper, we investigate the effect of providing social-network-based feedback intended to engender trainer competitiveness, focusing on its impact on the trainer's behavior. The results of our user study with 85 subjects show that the agent's social feedback can induce the trainer to train longer and give more feedback. Furthermore, the agent's performance was much better when social-competitive feedback was provided. The results also show that making the feedback active further increases the amount of time trainers spend training but does not further improve agent performance.

Book Title
AAMAS 2014: Proceedings of the Thirteenth International Joint Conference on Autonomous Agents and Multi−Agent Systems
Extended Abstract.