Agents
MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making Y ubin Kim
Foundation models are becoming valuable tools in medicine.
Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators
We provide theoretical guarantees for CBPR's rapid convergence to the optimal policy once human partners alter their policies.
Language-Driven Interactive Traffic Trajectory Generation
In this work, we propose InteractTraj, the first language-driven traffic trajectory generator that can generate interactive traffic trajectories.
Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
As a variant of the famous communication game Werewolf, One Night Ultimate W erewolf (ONUW) requires players to develop strategic discussion policies due to the potential role changes that increase the uncertainty and complexity of the game.
Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
However, existing unsupervised skill discovery methods often learn entangled skills where one skill variable simultaneously influences many entities in the environment, making downstream skill chaining extremely challenging.
