ML4EA

Part 2 · Chapter 11

Reinforcement Learning

Develops sequential decision-making from Markov decision processes through value, policy, actor-critic, and deep reinforcement learning methods.

Chapter map

What this chapter develops

  • Markov decision processes
  • Value functions
  • Q-learning and SARSA
  • Policy gradients
  • Actor-critic methods
  • Deep reinforcement learning

Engineering practice

Application and Diamond Examples

  1. 01

    Q-learning for adaptive cruise control

  2. 02

    SARSA traffic-light control

  3. 03

    Actor-critic chemical reactor control

  4. 04

    DDPG robot-arm control

Companion materials

Portal resources

Chapter catalogFind this chapter’s indexed examples and related topics.Application Example catalogOpen 7 validated notebooks with a verified portal account.AE datasetsReview dataset sources and generation details for this chapter's Application Examples.DiscussionAsk chapter-specific questions and compare engineering interpretations with other readers.