Deep reinforcement learning (RL) methods have driven impressive advances in artificial
intelligence in recent years, exceeding human performance in domains ranging from Atari to …

We review the psychology and neuroscience of reinforcement learning (RL), which has
experienced significant progress in the past two decades, enabled by the comprehensive …

Sequential decision making, commonly formalized as Markov Decision Process (MDP)
optimization, is an important challenge in artificial intelligence. Two key approaches to this …

Over the past 20 years, neuroscience research on reward-based learning has converged on
a canonical model, under which the neurotransmitter dopamine 'stamps in'associations …

The nervous system uses fast-and slow-adapting sensory detectors in parallel to enable
neuronal representations of external states and their temporal dynamics. It is unknown …

Theories of reward learning in neuroscience have focused on two families of algorithms
thought to capture deliberative versus habitual choice.'Model-based'algorithms compute the …

To make decisions, animals must evaluate candidate choices by accessing memories of
relevant experiences. Yet little is known about which experiences are considered or ignored …

Distinct model-free and model-based learning processes are thought to drive both typical
and dysfunctional behaviours. Data from two-stage decision tasks have seemingly shown …

Midbrain dopamine signals are widely thought to report reward prediction errors that drive
learning in the basal ganglia. However, dopamine has also been implicated in various …

Humans and animals are capable of evaluating actions by considering their long-run future
rewards through a process described using model-based reinforcement learning (RL) …