Reinforcement Learning: Algorithmic approach

Reinforcement Learning has been around with us for more than five decades now. Its effect on the modern world can be seen in advances in the field of artificial intelligence (AI).

Reinforcement Learning is a promising and popular branch of AI. It is possibly the most successful way to indicate computer imagination. It can be used in various problems, such as planning travels, making budgets, and business strategies. Reinforcement Learning is advantageous in that it allows us to control parts of the environment and also considers the portability of outcomes. It involves making smart models and agents that can learn ideal behavior on their own, based on the changing requirements.

Handbook of Reinforcement Learning: Algorithmic Approach covers the building block of reinforcement learning. This book comprehensively presents reinforcement learning for a tabular case. This book also covers both learning and planning methods. We present several value-based methods such as UCB, SARSA, Q-learning, etc. We also have extended these ideas to function approximation. We have presented artificial neural networks, LSTD, gradient, emphatic TD methods, average reward methods, policy gradient methods, etc.

The content of the book has been beautifully presented. It avoids creating any sort of confusion in the readers’ minds. By the end of the book, you will have worked with major reinforcement learning algorithms to solve real-world problems.