This page is may be out of date. You can find an up-to-date list of my articles on my Google Scholar profile.
N-Agent Ad Hoc Teamwork
Recommended citation: Caroline Wang, Arrasy Rahman, Ishan Durugkar, Elad Liebman, Peter Stone. "N-Agent Ad Hoc Teamwork." NeurIPS 2024.
TLDR: Existing paradigms for multi-agent coordination are limited by assuming that either all agents are controlled (e.g. the typical cooperative MARL algorithm), or that only a single agent is controlled (ad hoc teamwork / zero shot coordination). We pose the N-Agent Ad Hoc Teamwork (NAHT) problem to the community, to lift these restrictions and pave the path towards more open multi-agent learning paradigms. Read more
Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning
Recommended citation: Zizhao Wang*, Caroline Wang*, Xuesu Xiao, Yuke Zhu, Peter Stone (2024). "Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning." AAAI 2024.
TLDR: We introduce Causal Bisimulation Learning (CBM), a method that learns the causal relationships in the dynamics and reward functions for each task to derive a minimal, task-specific abstraction. Read more
D-Shape: Demonstration Shaped Reinforcement Learning
Recommended citation: Caroline Wang, Garrett Warnell, Peter Stone (2023). "D-Shape: Demonstration Shaped Reinforcement Learning." AAMAS 2023.
TLDR: TLDR: We propose D-Shape, an RL+IL algorithm that allows learning from suboptimal demonstrations while retaining the ability to find the optimal policy with respect to the task reward. Read more
DM$^2$: Distributed multi-agent reinforcement learning via distribution matching
Recommended citation: Caroline Wang*, Ishan Durugkar*, Elad Liebman*, Peter Stone. "DM$^2$: Distributed Multi-Agent Reinforcement Learning via Distribution Matching." AAAI 2023.
TLDR: We propose DM$^2$, an algoritm that allows a team of agents to perform cooperative tasks by independently imitating corresponding experts agents from a team of experts. Read more
In pursuit of interpretable, fair and accurate machine learning for criminal recidivism prediction
Recommended citation: Caroline Wang*, Bin Han*, Bhrij Patel, Feroze Mohideen, Cynthia Rudin (2022). "In pursuit of interpretable, fair and accurate machine learning for criminal recidivism prediction." Journal of Quantitative Criminology.
TLDR: We design various interpretable machine learning models to predict criminal recidivism. Read more
Broader issues surrounding model transparency in criminal justice risk scoring
Recommended citation: Cynthia Rudin, Caroline Wang, Beau Coker (2020). "Broader issues surrounding model transparency in criminal justice risk scoring." HDSR. 2(1).
TLDR: A rejoinder to, “The age of secrecy and unfairness in criminal recidivism prediction”. Read more
The age of secrecy and unfairness in recidivism prediction
Recommended citation: Cynthia Rudin, Caroline Wang, and Beau Coker (2020). "The age of secrecy and unfairness in recidivism prediction." HDSR. 2(1).
TLDR: We investigate the COMPAS model—a black-box recidivism prediction model used widely in America’s justice system. Read more