Mycal Tucker

Interpretable Learned Emergent Communication for Human-Agent Teams

2022 · arXiv (Cornell University)

Learning interpretable communication is essential for multi-agent and human-agent teams (HATs). In multi-agent reinforcement learning for partially-observable environments, agents may convey information to others via learned communication, allowing the team to complete its task. Inspired …

An Information Bottleneck Characterization of the Understanding-Workload Tradeoff

2023 · arXiv (Cornell University)

Recent advances in artificial intelligence (AI) have underscored the need for explainable AI (XAI) to support human understanding of AI systems. Consideration of human factors that impact explanation efficacy, such as mental workload and human …