July 2024
Intermediate to advanced
650 pages
17h 23m
English
This is the last chapter of the book. Throughout the book, I have discussed in-depth many foundational aspects of reinforcement learning (RL). You learned about MDP and planning in MDP using dynamic planning. You learned about model-free value methods. You learned about scaling up solution techniques using function approximation, specifically with deep learning–based approaches such as DQN. The book also covered policy-based methods such as REINFORCE, TRPO, PPO, and so on, as well as unification ...
