An Introduction to Deep Reinforcement Learning
暫譯: 深度強化學習入門

The current era of artificial intelligence and machine learning (AIML) tools has transformed the workings of vast swaths of our private, working, and social lives beyond recognition. It has been found that these tools can solve many problems in better and faster ways compared to humans. AIML tools allow machines and related systems to reason and infer almost like humans, and this has deep intellectual and philosophical ramifications as well. The areas of machine learning are broadly classified into supervised, unsupervised, and deep reinforcement learning (DRL). The last one comes closest to how humans reason, and various innovations in this area have many useful applications.

This book covers most of the areas of DRL, with a special focus on its mathematical and algorithmic foundations. Undergraduate and early graduate students should find it to be a good guide to the fast-developing areas of DRL and its myriad applications in both technical and social contexts.