Since its introduction, the reward prediction error theory of dopamine has explained a wealth
of empirical phenomena, providing a unifying framework for understanding the …

Learning about rewards and punishments is critical for survival. Classical studies have
demonstrated an impressive correspondence between the firing of dopamine neurons in the …

Many reinforcement learning (RL) problems in practice are offline, learning purely from
observational data. A key challenge is how to ensure the learned policy is safe, which …

We analyse quantile temporal-difference learning (QTD), a distributional reinforcement
learning algorithm that has proven to be a key component in several successful large-scale …

Safety is critical to broadening the real-world use of reinforcement learning. Modeling the
safety aspects using a safety-cost signal separate from the reward and bounding the …

When faced with sequential decision-making problems, it is often useful to be able to predict
what would happen if decisions were made using a new policy. Those predictions must …

The hypothesis that midbrain dopamine (DA) neurons broadcast a reward prediction error
(RPE) is among the great successes of computational neuroscience. However, recent …

Reinforcement learning has a rich history in neuroscience, from early work on dopamine as
a reward prediction error signal for temporal difference learning (Schultz et al., 1997) to …

Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by
effectively utilizing previously collected data. Most existing offline RL algorithms use …

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 …