Will Reinforcement Learning Pave the Way for Accessible True Artificial Intelligence?
Python Machine Learning, Third Edition covers the essential concepts of reinforcement learning, starting from its foundations, and how RL can support decision making in complex environments. Read more on the topic from the book's author Sebastian Raschka.
Sebastian Raschka, author of the bestselling book Python Machine Learning, Third Edition dissects the genesis of reinforcement learning.
Reinforcement learning (RL) has received a massive boost in attention recently. Thanks to impressive projects such as DeepMind's AlphaGo and AlphaGo Zero, which beat the world's best players in the strategy board game “Go”, RL has garnered extensive news coverage. Just recently, RL was used to compete with the world's top e-sports players in the real-time strategy video game StarCraft II.
Python Machine Learning, Third Edition covers the essential concepts of RL, starting from its foundations, and how RL can support decision making in complex environments. The book discusses agent-environment interactions and Markov decision processes (MDP), and considers three main approaches for solving RL problems: dynamic programming, MC learning, and TD learning. It discusses how the dynamic programming algorithm assumes that the full knowledge of environment dynamics is available, an assumption that is not typically true for most real-world problems.
Furthermore, the book reveals how the MC- and TD-based algorithms learn by allowing an agent to interact with the environment and generate a simulated experience. After discussing the underlying theory, it applies the Q-learning algorithm as an off-policy subcategory of the TD algorithm for solving the grid world example. Finally, the book covers the concepts of function approximation and deep Q-learning in particular, which can be used for problems with large or continuous state spaces.
To answer the question of whether RL will lead to true artificial intelligence, I think we are still extremely far away. As of today, there is no clear path towards achieving artificial general intelligence or even predicting a rough time estimate for when we will get there.
I would argue that the closest we’ve gotten to human-level performance in complex tasks is AlphaGo and AlphaStar, which are both based on RL. However, a model like AlphaGo that can beat players in a complex board game cannot be compared to human-level thinking—it cannot even generalize to other, related tasks without retraining the model from scratch.
I have added a new chapter dedicated to reinforcement learning in the latest edition of my book Python Machine Learning, Third Edition to provide an accessible and practical introduction to this exciting field. I hope that the achievements of RL recently reported in the news may inspire learners to explore this topic.
About the Author
Sebastian Raschka is an Assistant Professor of Statistics at the University of Wisconsin-Madison focusing on machine learning and deep learning research. Some of his recent research methods have been applied to solving problems in the field of biometrics for imparting privacy to face images.