Standard exploration methods typically rely on random coverage of the state space or
coverage-promoting exploration bonuses. However, in partially observed settings, the …

We develop a general theory to optimize the frequentist regret for sequential learning
problems, where efficient bandit and reinforcement learning algorithms can be derived from …

All biological and artificial agents must act given limits on their ability to acquire and process
information. As such, a general theory of adaptive behavior should be able to account for the …

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

In this paper, we prove state-of-the-art Bayesian regret bounds for Thompson Sampling in
reinforcement learning in a multitude of settings. We present a refined analysis of the …

We investigate the extent to which offline demonstration data can improve online learning. It
is natural to expect some improvement, but the question is how, and by how much? We …

Policy optimization from batch data, ie, offline reinforcement learning (RL) is important when
collecting data from a current policy is not possible. This setting incurs distribution mismatch …

Expected free energy (EFE) is a central quantity in active inference which has recently
gained popularity due to its intuitive decomposition of the expected value of control into a …

A popular perspective in Reinforcement learning (RL) casts the problem as probabilistic
inference on a graphical model of the Markov decision process (MDP). The core object of …

This work designs and analyzes a novel set of algorithms for multi-agent reinforcement
learning (MARL) based on the principle of information-directed sampling (IDS). These …