In a standard view of the reinforcement learning problem, an agent's goal is to efficiently
identify a policy that maximizes long-term reward. However, this perspective is based on a …

Reinforcement learning (RL) has demonstrated remarkable achievements in simulated
environments. However, carrying this success to real environments requires the important …

Reinforcement learning from human feedback (RLHF) has emerged as a reliable approach
to aligning large language models (LLMs) to human preferences. Among the plethora of …

The reward hypothesis posits that," all of what we mean by goals and purposes can be well
thought of as maximization of the expected value of the cumulative sum of a received scalar …

This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement
learning and sequential decision making, covering value-based RL, policy-gradient …

An agent that efficiently accumulates knowledge to develop increasingly sophisticated skills
over a long lifetime could advance the frontier of artificial intelligence capabilities. The …

In this review/tutorial article, we present recent progress on optimal control of partially
observed Markov Decision Processes (POMDPs). We first present regularity and continuity …

The quintessential model-based reinforcement-learning agent iteratively refines its
estimates or prior beliefs about the true underlying model of the environment. Recent …

Modern reinforcement learning has been conditioned by at least three dogmas. The first is
the environment spotlight, which refers to our tendency to focus on modeling environments …

A default assumption in the design of reinforcement-learning algorithms is that a decision-
making agent always explores to learn optimal behavior. In sufficiently complex …