Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
The Convention Gap: Towards Measuring Implicit Communication in Cooperative AI Evaluation
Makoto Fukushima, Hua-Dong Xiong, Ehsan Moradi Pari
Cooperative AI agents are evaluated against other AIs, yet human cooperation relies on implicit conventions -- shared protocols for reading meaning beyond the literal message -- wh…
cs.AI2024
Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models
Muhan Lin, Shuyang Shi, Yue Guo +6
The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and m…