学习笔记 | UCL Course on RL

Lecture 1

Video: https://www.youtube.com/watch?v=2pWv7GOvuf0

Slide: Introduction to Reinforcement Learning

Key points:

1. An RL agent may include one or more of these components:

• Policy: agent’s behaviour function
• Value function: how good is each state and/or action
• Model: agent’s representation of the environment

2. Two fundamental problems in sequential decision making

• Reinforcement Learning
  • environment is unknown
  • the agent interacts with the environment
  • the agent improves its policy
• Planning
  • environment is known
  • the agent performs computations with its model
  • the agent improves its policy
  • aka diliberation, reasoning, introspection, pondering, thought

Jan 17, 2017