As a subfield of machine learning, reinforcement learning (RL) aims at optimizing decision
making by using interaction samples of an agent with its environment and the potentially …

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

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 …

Learning goal-directed behavior in environments with sparse feedback is a major challenge
for reinforcement learning algorithms. One of the key difficulties is insufficient exploration …

Autonomous cyber-physical systems (CPS) can improve safety and efficiency for safety-
critical applications, but require rigorous testing before deployment. The complexity of these …

The increasing abundance of large high-quality datasets, combined with significant
technical advances over the last several decades have made machine learning into a major …

Research on artificial intelligence in the last two decades has greatly improved performance
of both manufacturing and service systems. Currently, there is a dire need for an article that …

We study the use of randomized value functions to guide deep exploration in reinforcement
learning. This offers an elegant means for synthesizing statistically and computationally …

We study the sample complexity of model-based reinforcement learning (henceforth RL) in
general contextual decision processes that require strategic exploration to find a near …

The recent adaptation of deep neural network-based methods to reinforcement learning and
planning domains has yielded remarkable progress on individual tasks. Nonetheless …