Robot Learning in Mixed Adversarial and Collaborative Settings

Abstract

Previous work has shown that interacting with a human adversary can significantly improve the efficiency of the learning process in robot grasping. However, people are not consistent in applying adversarial forces; instead they may alternate between acting antagonistically with the robot or helping the robot achieve its tasks. We propose a physical framework for robot learning in a mixed adversarial/collaborative setting, where a second agent may act as a collaborator or as an antagonist, unbeknownst to the robot. The framework leverages prior estimates of the reward function to infer whether the actions of the second agent are collaborative or adversarial. Integrating the inference in an adversarial learning algorithm can significantly improve the robustness of learned grasps in a manipulation task.