Reinforcement Learning (RL) from Human Preference-based feedback is a popular
paradigm for fine-tuning generative models, which has produced impressive models such as …

Three major challenges in reinforcement learning are the complex dynamical systems with
large state spaces, the costly data acquisition processes, and the deviation of real-world …

This paper studies multi-agent reinforcement learning in Markov games, with the goal of
learning Nash equilibria or coarse correlated equilibria (CCE) sample-optimally. All prior …

We consider the problem of decentralized multi-agent reinforcement learning in Markov
games. A fundamental question is whether there exist algorithms that, when run …

We consider online reinforcement learning (RL) in episodic Markov decision processes
(MDPs) under the linear $ q^\pi $-realizability assumption, where it is assumed that the …

A fundamental question in reinforcement learning theory is: suppose the optimal value
functions are linear in given features, can we learn them efficiently? This problem's …

Low-complexity models such as linear function representation play a pivotal role in enabling
sample-efficient reinforcement learning (RL). The current paper pertains to a scenario with …

We consider approximate dynamic programming in $\gamma $-discounted Markov decision
processes and apply it to approximate planning with linear value-function approximation …

We propose a new stochastic primal-dual optimization algorithm for planning in a large
discounted Markov decision process with a generative model and linear function …

In this paper, we define, evaluate, and improve the``relay-generalization''performance of
reinforcement learning (RL) agents on the out-of-distribution``controllable''states. Ideally, an …