The Evolution of Sequential Decision Making: From MDP to RL and Beyond

Dive into the evolution of sequential decision making, from MDP to RL, and discover the new universal framework. Learn about the latest developments and the four classes of policies. Download a free chapter from the book webpage.

Explore the evolution of sequential decision making from Markov Decision Processes (MDP) to Reinforcement Learning (RL) and the universal framework. Learn about the shift from Bellman’s equation to a variety of policies, and the four classes of policies that include any method for making decisions. Discover the latest developments in the field with the new book by a leading expert.

Tags: sequential decision making, MDP, RL, Bellman’s equation, policy gradient theorem, Monte Carlo tree search, universal framework