What are the functionals of the reward that can be computed and optimized exactly in
Markov Decision Processes? In the finite-horizon, undiscounted setting, Dynamic …

In classic Reinforcement Learning (RL), the agent maximizes an additive objective of the
visited states, eg, a value function. Unfortunately, objectives of this type cannot model many …

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 …

This article introduces the theory of offline reinforcement learning in large state spaces,
where good policies are learned from historical data without online interactions with the …

We propose a reinforcement learning (RL) approach to address a multiperiod optimization
problem in which a portfolio manager seeks an optimal constant proportion portfolio strategy …

In this thesis, we address general utility Markov decision processes (GUMDPs), which
generalize the standard Markov decision processes (MDPs) framework for decision-making …

In this paper, we study reinforcement learning from human feedback (RLHF) under an
episodic Markov decision process with a general trajectory-wise reward model. We …

We consider inverse reinforcement learning problems with concave utilities. Concave Utility
Reinforcement Learning (CURL) is a generalisation of the standard RL objective, which …

The widely used expected utility theory has been shown to be empirically inconsistent with
human preferences in the psychology and behavioral economy literatures. Cumulative …

How can a scientist use a Reinforcement Learning (RL) algorithm to design experiments
over a dynamical system's state space? In the case of finite and Markovian systems, an area …