… -learning learning algorithms) in AI-GAs [7]. However, we aim to achieve generalisation
not just across tasks but also across different domains. Learning domain-invariant algorithms …

… Reinforcement learning is of great … algorithms of reinforcement learning that build on the
powerful theory of dynamic programming. We give a fairly comprehensive catalog of learning …

… Reinforcement learning … reinforcement learning techniques for tackling dynamically changing
environment contexts in a system. The focus is on a single autonomous RL agent learning …

… well-known issue for reinforcement learning (RL) algorithms. This … Reinforcement Learning
algorithms vary widely in design, … certain notions that should span the gamut of RL algorithms. …

… guide to rigorous comparisons of reinforcement learning algorithms. After introducing the
concepts … guidelines and code to perform rigorous comparisons of RL algorithm performances. …

… and batch reinforcement learning algorithms under unified … We find that under these
conditions, many of these algorithms … Batch-Constrained Q-learning algorithm to a discrete-action …

… different types of reinforcement learning algorithms and present definitions. At a high level,
all standard reinforcement learning algorithms follow the same basic learning loop: the agent …

… deep learning and reinforcement learning algorithms. Speakers contributed to provide talks
about their recent studies that can be key technologies to achieve human-level intelligence. …

… In recent years, Deep Reinforcement Learning (DRL) algorithms have achieved great suc…
Nevertheless, understanding all the implementation details of an algorithm remains difficult …

… a model-free learning algorithm to learn an approximately optimal policy. We propose the
use of Q-learning (QL) [44], a model-free iterative RL algorithm to obtain the experience tuples. …