Claire Liang

Shen Li, Yuyang Zhang, Zhaolin Ren et al.

Interactive preference learning systems infer human preferences by presenting queries as pairs of options and collecting binary choices. Although binary choices are simple and widely used, they provide limited information about preference strength. To address this, we leverage human response times, which are inversely related to preference strength, as an additional signal. We propose a computationally efficient method that combines choices and response times to estimate human utility functions, grounded in the EZ diffusion model from psychology. Theoretical and empirical analyses show that for queries with strong preferences, response times complement choices by providing extra information about preference strength, leading to significantly improved utility estimation. We incorporate this estimator into preference-based linear bandits for fixed-budget best-arm identification. Simulations on three real-world datasets demonstrate that using response times significantly accelerates preference learning compared to choice-only approaches. Additional materials, such as code, slides, and talk video, are available at https://shenlirobot.github.io/pages/NeurIPS24.html

Claire Liang, Wil Thomason, E. Andy Ricci et al.

In environments where multiple robots must coordinate in a shared space, decentralized approaches allow for decoupled planning at the cost of global guarantees, while centralized approaches make the opposite trade-off. These solutions make a range of assumptions - commonly, that all the robots share the same planning strategies. In this work, we present a framework that ensures progress for all robots without assumptions on any robot's planning strategy by (1) generating a partition of the environment into "flow", "open", and "passage" regions and (2) imposing a set of rules for robot motion in these regions. These rules for robot motion prevent deadlock through an adaptively centralized protocol for resolving spatial conflicts between robots. Our proposed framework ensures progress for all robots without a grid-like discretization of the environment or strong requirements on robot communication, coordination, or cooperation. Each robot can freely choose how to plan and coordinate for itself, without being vulnerable to other robots or groups of robots blocking them from their goals, as long as they follow the rules when necessary. We describe our space partition and motion rules, prove that the motion rules suffice to guarantee progress in partitioned environments, and demonstrate several cases in simulated polygonal environments. This work strikes a balance between each robot's planning independence and a guarantee that each robot can always reach any goal in finite time.