Wanting to be Understood
This work addresses the challenge of developing more socially aware AI agents, though it is incremental as it builds on existing paradigms like active inference and intrinsic motivation.
The paper tackles the problem of fostering social interaction and cooperation in reinforcement learning agents by proposing intrinsic motivations for mutual understanding, showing that rewards for reciprocal understanding lead agents to prioritize interaction and facilitate cooperation in asymmetric reward tasks.
This paper explores an intrinsic motivation for mutual awareness, hypothesizing that humans possess a fundamental drive to understand and to be understood even in the absence of extrinsic rewards. Through simulations of the perceptual crossing paradigm, we explore the effect of various internal reward functions in reinforcement learning agents. The drive to understand is implemented as an active inference type artificial curiosity reward, whereas the drive to be understood is implemented through intrinsic rewards for imitation, influence/impressionability, and sub-reaction time anticipation of the other. Results indicate that while artificial curiosity alone does not lead to a preference for social interaction, rewards emphasizing reciprocal understanding successfully drive agents to prioritize interaction. We demonstrate that this intrinsic motivation can facilitate cooperation in tasks where only one agent receives extrinsic reward for the behaviour of the other.