The emergence of powerful artificial intelligence (AI) is defining new research directions in
neuroscience. To date, this research has focused largely on deep neural networks trained …

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

Deep reinforcement learning (RL) has achieved outstanding results in recent years. This has
led to a dramatic increase in the number of applications and methods. Recent works have …

Abstract We introduce Phasic Policy Gradient (PPG), a reinforcement learning framework
which modifies traditional on-policy actor-critic methods by separating policy and value …

Many reinforcement learning (RL) tasks provide the agent with high-dimensional
observations that can be simplified into low-dimensional continuous states. To formalize this …

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 …

Since the introduction of DQN, a vast majority of reinforcement learning research has
focused on reinforcement learning with deep neural networks as function approximators …

In reinforcement learning (RL), function approximation errors are known to easily lead to the-
value overestimations, thus greatly reducing policy performance. This article presents a …

Bootstrap** is a core mechanism in Reinforcement Learning (RL). Most algorithms, based
on temporal differences, replace the true value of a transiting state by their current estimate …

In this work, we study the simple yet universally applicable case of reward sha** in value-
based Deep Reinforcement Learning (DRL). We show that reward shifting in the form of a …