… In this paper, we firstly survey the model and theory of reinforcement learning. Then, we
roundly present the main reinforcement learning algorithms, including Sarsa, … Q-learning …

… 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 …

… -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 …

… This paper surveys the field of reinforcement learning from a … to researchers familiar with
machine learning. Both the historical … algorithms in this section address the problem of learning …

… , such as learning to play video games just from pixel information, are now successfully solved
using deep reinforcement learning. … model-free RL algorithms and pathbreaking function …

… Abstract--Most of the research in reinforcement learning has … a stochastic reinforcement
learning algorithm.~br learning[… Learning takes place bv using our algorithm to arlfl,st the two …

… the most appropriate algorithm from the set for a given problem instance. We show how a
reinforcement learning approach can be used to select the right algorithm for each instance at …

… using the same algorithm and network … reinforcement learning algorithm can learn, tabula
rasa—without domain-specific human knowledge or data, as evidenced by the same algorithm …

… Temporal difference learning algorithms are fundamental for evaluating/predicting value …
Control algorithms find optimal policies. Reinforcement learning algorithms may be based on …

… has similarly accelerated progress in RL, with the use of deeplearning algorithms within RL
defining the field of DRL. The aim of this survey is to cover both seminal and recent develop…