This is the last chapter of the book. Throughout the book, we have dived deep into many foundational aspects of reinforcement learning (RL). We looked at MDP and at planning in MDP using dynamic planning. We looked at model-free value methods. We talked about scaling up solution techniques using function approximation specifically by using deep learning–based approaches such as DQN. We looked at policy-based methods such as REINFORCE, TRPO, PPO, etc. We unified value and policy optimization methods in the actor-critic (AC) approach. Finally, we looked at how to ...
© Nimish Sanghi 2021
N. SanghiDeep Reinforcement Learning with Pythonhttps://doi.org/10.1007/978-1-4842-6809-4_1010. Further Exploration and Next Steps
Nimish Sanghi1
(1)
Bangalore, India
Get Deep Reinforcement Learning with Python: With PyTorch, TensorFlow and OpenAI Gym now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
