3

We apply functional acceleration to the Policy Mirror Descent (PMD) general family of algorithms, which cover a wide range of novel and …

Continual Reinforcement Learning (CRL) aims to develop algorithms that adapt to non-stationary sequences of tasks. A promising recent …

Serotonergic psychedelics have been identified as promising next-generation therapeutic agents in the treatment of mood and anxiety …

We work towards a unifying paradigm for accelerating policy optimization methods in reinforcement learning (RL) by integrating …

As policy gradient methods can suffer from high variance, it is common to replace the Monte-Carlo estimate of the return with a critic …

Efficient credit assignment is essential for reinforcement learning algorithms in both prediction and control settings. We describe a …