Reinforcement Learning Foundations

Description

In this course, you will :

• Khaulat Abdulhakeem, your instructor, will teach you the fundamentals of this relatively new but valuable skill.
• Learn about the key terminology used in RL, how RL contributes to the advancement of AI, and the types of problems you can solve using RL. Khaulat demonstrates how to define and visualise reinforcement learning problems.
• RL algorithms, such as the Monte Carlo and temporal difference methods, are also covered.
• investigates deep and multi-agent RL, as well as how inverse learning works and how it can assist agents in learning by imitation.

Syllabus :

1. Getting Started with Reinforcement Learning

• Terms in reinforcement learning
• A basic RL problem
• Markov decision process
• A basic RL solution

 

2. Reinforcement Learning Algorithms

• Monte Carlo method
• Temporal difference methods
• Other RL algorithms

 

3. Monte Carlo Method

• The setting
• Exploration and exploitation
• Monte Carlo prediction
• First visit and every visit MC prediction
• Monte Carlo control
• Additional modifications

 

4. Temporal Difference Methods

• The setting
• SARSA
• SARSAMAX (Q-learning)
• Expected SARSA

 

5. Modified Forms of Reinforcement

• Deep reinforcement learning
• Multi-agent reinforcement learning
• Inverse reinforcement learning

Show more