The combination of reinforcement learning with deep learning is a promising approach to
tackle important sequential decision-making problems that are currently intractable. One …

In recent years, the deep reinforcement learning (DRL) algorithms have been developed
rapidly and have achieved excellent performance in many challenging tasks. However, due …

Unifying seemingly disparate algorithmic ideas to produce better performing algorithms has
been a longstanding goal in reinforcement learning. As a primary example, TD (λ) elegantly …

Deep reinforcement learning (RL) algorithms have recently achieved remarkable successes
in various sequential decision making tasks, leveraging advances in methods for training …

In the model-based policy search approach to reinforcement learning (RL), policies are
found using a model (or" simulator") of the Markov decision process. However, for high …

Solving a reinforcement learning (RL) problem poses two competing challenges: fitting a
potentially discontinuous value function, and generalizing well to new observations. In this …

In recent years there have been many successes of using deep representations in
reinforcement learning. Still, many of these applications use conventional architectures …

We study the reward-free reinforcement learning framework, which is particularly suitable for
batch reinforcement learning and scenarios where one needs policies for multiple reward …

In this chapter, we introduce and summarize the taxonomy and categories for reinforcement
learning (RL) algorithms. Figure 3.1 presents an overview of the typical and popular …

To make reinforcement learning algorithms run in a reasonable amount of time, it is
frequently necessary to use a well-chosen reward function that gives appropriate “hints” to …