15 papers
OR-Transformer: Scaling Real-Time Decision-Making to 1,000 Items
Shuze Daniel Liu, David Simchi-Levi, Claire Chen +2
Modern supply chain operations can require coordinating replenishment across thousands of heterogeneous items under correlated stochastic demand, heterogeneous lead times, and shar…
Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation
Claire Chen, Shuze Daniel Liu, Licheng Luo +3
In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate this issue, behavior policy s…
Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations
Shuze Daniel Liu, Claire Chen, Jiabao Sean Xiao +2
Negotiation is a fundamental strategic interaction in management science, characterized by agents attempting to reach agreements while protecting private information, such as reser…
Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning
Vagul Mahadevan, Claire Chen, Shuze Daniel Liu +1
This work studies the convergence of two-timescale stochastic approximations (SA), a class of iterative algorithms that update two sets of parameters in fast and slow timescales re…
Fast Rates in -Potential Games via Regularized Mirror Descent
Claire Chen, Yuheng Zhang
An -potential game is a multi-player non-cooperative interaction in which a global potential function approximates individual player rewards up to a structural bias . While i…
Pessimism-Free Offline Learning in General-Sum Games via KL Regularization
Claire Chen, Yuheng Zhang
Offline multi-agent reinforcement learning in general-sum settings is challenged by the distribution shift between logged datasets and target equilibrium policies. While standard m…
Beyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement Learning
Zixuan Xie, Xinyu Liu, Claire Chen +3
In-context reinforcement learning (ICRL) studies agents that, after pretraining, adapt to new tasks by conditioning on additional context without parameter updates. Existing theore…
Offline Two-Player Zero-Sum Markov Games with KL Regularization
Claire Chen, Yuheng Zhang, Xinyu Liu +3
We study the problem of learning Nash equilibria in offline two-player zero-sum Markov games. While existing approaches often rely on explicit pessimism to address distribution shi…
Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
Jiuqi Wang, Jayanth Srinivasa, Claire Chen +3
Deep continual learning requires models to adapt to new tasks without retraining from scratch. However, neural networks can lose their ability to adapt to new tasks after training…
Beyond Pessimism: Offline Learning in KL-regularized Games
Yuheng Zhang, Claire Chen, Nan Jiang
We study offline learning in KL-regularized two-player zero-sum games, where policies are optimized with respect to a fixed reference policy through KL regularization. Prior work r…
AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification
Claire Chen, Jiabao Sean Xiao, Shuze Daniel Liu +7
Modern astronomical observatories generate a massive volume of multimodal data, creating a critical bottleneck for expert human review. While multimodal large language models (LLMs…
Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards
Shuze Daniel Liu, Claire Chen, Jiabao Sean Xiao +4
The recent advancement of Large Language Models (LLMs) has established their potential as autonomous interactive agents. However, they often struggle in strategic games of incomple…
MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics
Xinyu Liu, Zixuan Xie, Amir Moeini +5
While the ecosystem of Lean and Mathlib has enjoyed celebrated success in formal mathematical reasoning with the help of large language models (LLMs), the absence of many folklore…
Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning
Claire Chen, Shuze Daniel Liu, Shangtong Zhang
In reinforcement learning, classic on-policy evaluation methods often suffer from high variance and require massive online data to attain the desired accuracy. Previous studies att…
Doubly Optimal Policy Evaluation for Reinforcement Learning
Shuze Daniel Liu, Claire Chen, Shangtong Zhang
Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential na…