Deep Reinforcement Learning with Python: RLHF for Chatbots and Large Language Models

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2024

N. SanghiDeep Reinforcement Learning with Pythonhttps://doi.org/10.1007/979-8-8688-0273-7_3

3. Model-Based Approaches

Nimish Sanghi¹  

(1)

Bangalore, India

 

Chapter 2 talked about the parts of the setup that form the agent and the part that forms the environment. To recap, the agent gets the state S_t = s and follows a policy π(s| a) that maps states to actions. The agent uses this policy to take an action A_t = a when in state S_t = s. The system transitions to the next time instant of t + 1. The environment responds to the action (A_t = a) by putting the agent in a new state of S_t + 1 = s^′ and providing feedback to the agent in terms of a reward, R_t + 1. The agent ...