7 papers
When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
Jose Efraim Aguilar Escamilla, Haoyang Hong, Jiawei Li +4
We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target RL agent to adopt a policy t…
Accelerating RL for LLM Reasoning with Optimal Advantage Regression
Kianté Brantley, Mingyu Chen, Zhaolin Gao +4
Reinforcement learning (RL) has emerged as a powerful tool for fine-tuning large language models (LLMs) to improve complex reasoning abilities. However, state-of-the-art policy opt…
Avoiding scaling in RLHF through Preference-based Exploration
Mingyu Chen, Yiding Chen, Wen Sun +1
Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for large language model (LLM) alignment. This paper studies the setting of online RLHF and foc…
State-free Reinforcement Learning
Mingyu Chen, Aldo Pacchiano, Xuezhou Zhang
In this work, we study the \textit{state-free RL} problem, where the algorithm does not have the states information before interacting with the environment. Specifically, denote th…
Scale-free Adversarial Reinforcement Learning
Mingyu Chen, Xuezhou Zhang
This paper initiates the study of scale-free learning in Markov Decision Processes (MDPs), where the scale of rewards/losses is unknown to the learner. We design a generic algorith…
Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback
Canzhe Zhao, Ruofeng Yang, Baoxiang Wang +2
In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting. In particular, the unknown transition probability kernel admits…
Improved Algorithms for Adversarial Bandits with Unbounded Losses
Mingyu Chen, Xuezhou Zhang
We consider the Adversarial Multi-Armed Bandits (MAB) problem with unbounded losses, where the algorithms have no prior knowledge on the sizes of the losses. We present UMAB-NN and…