Abstract Reinforcement learning from Human Feedback (RLHF) learns from preference
signals, while standard Reinforcement Learning (RL) directly learns from reward signals …

Finding unified complexity measures and algorithms for sample-efficient learning is a central
topic of research in reinforcement learning (RL). The Decision-Estimation Coefficient (DEC) …

Reinforcement Learning algorithms that learn from human feedback (RLHF) need to be
efficient in terms of statistical complexity, computational complexity, and query complexity. In …

This paper studies the fundamental limits of reinforcement learning (RL) in the challenging
partially observable setting. While it is well-established that learning in Partially Observable …

A central problem in the theory of multi-agent reinforcement learning (MARL) is to
understand what structural conditions and algorithmic principles lead to sample-efficient …

This paper investigates posterior sampling algorithms for competitive reinforcement learning
(RL) in the context of general function approximations. Focusing on zero-sum Markov games …

Partial Observability--where agents can only observe partial information about the true
underlying state of the system--is ubiquitous in real-world applications of Reinforcement …

Policy gradient methods enjoy strong practical performance in numerous tasks in
reinforcement learning. Their theoretical understanding in multiagent settings, however …

The general sequential decision-making problem, which includes Markov decision
processes (MDPs) and partially observable MDPs (POMDPs) as special cases, aims at …

In many multi-agent and high-dimensional robotic tasks, the controller can be designed in
either a centralized or decentralized way. Correspondingly, it is possible to use either single …