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_3

3. Model-Based Algorithms

Nimish Sanghi¹  

(1)

Bangalore, India

 

In Chapter 2, we talked about the parts of the setup that form the agent and the part that forms the environment. The agent gets the state S_t = s and learns 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 has no control over what the new state S_t + 1 and reward R_t + 1 will be. ...