Deep Reinforcement Learning with Python: With PyTorch, TensorFlow and OpenAI Gym

© Nimish Sanghi 2021

N. SanghiDeep Reinforcement Learning with Pythonhttps://doi.org/10.1007/978-1-4842-6809-4_9

9. Integrated Planning and Learning

Nimish Sanghi¹  

(1)

Bangalore, India

 

Studying topics separately followed by learning about them together has been a recurring theme in this book. We first looked at model-based algorithms in Chapter 3. Using this setup, we knew the model dynamics of the world in which the agent was operating. The agent used the knowledge of model dynamics along with Bellman equations to first carry out the evaluation/prediction task to learn the state or state-action values. It then followed this up by improving the policy to get the optimal behavior, which was called policy improvement/policy iteration . Once we know ...