Centralised training with decentralised execution is an important setting for cooperative
deep multi-agent reinforcement learning due to communication constraints during execution …

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before
deploying them to safety-critical applications. Previous primal-dual style approaches suffer …

There are two main ways to discover or design small drug molecules. The first involves fine-
tuning existing molecules or commercially successful drugs through quantitative structure …

Active inference is a Bayesian framework for understanding biological intelligence. The
underlying theory brings together perception and action under one single imperative …

Active Inference is a theory arising from theoretical neuroscience which casts action and
planning as Bayesian inference problems to be solved by minimizing a single quantity—the …

Abstract Recent Reinforcement Learning (RL) algorithms making use of Kullback-Leibler
(KL) regularization as a core component have shown outstanding performance. Yet, only …

Recent studies in reinforcement learning (RL) have made significant progress by leveraging
function approximation to alleviate the sample complexity hurdle for better performance …

Adversarial binaries are executable files that have been altered without loss of function by
an AI agent in order to deceive malware detection systems. Progress in this emergent vein of …

Information sharing is key in building team cognition and enables coordination and
cooperation. High-performing human teams also benefit from acting strategically with …

Imitation learning methods seek to learn from an expert either through behavioral cloning
(BC) for the policy or inverse reinforcement learning (IRL) for the reward. Such methods …