- Overview of Reinforcement Learning: Familiarize yourself with reinforcement learning concepts and the course.
- Defining the Environment: Define how an agent interacts with an environment model.
- Defining Agents: Create representations of RL agents.
- Training Agents: Use simulation episodes to train an agent.
- Conclusion: Learn next steps and give feedback on the course.
Overview
Syllabus
- What is Reinforcement Learning
- Simulating with a Pretrained Agent
- Components of a Reinforcement Learning Model
- Defining an Environment Interface
- Providing Rewards
- Including Actions in the Reward
- Connecting a Simulink Environment to a MATLAB Agent
- Critics and Q Values
- Representing Critics for Continuous Problems
- Creating Neural Networks
- Creating Networks for Agents
- Actors and Critics
- Creating Default Agent Representations
- Summary of Agents
- Training
- Changing Options
- Improving Training
- Summary of Functions
- Additional Resources
- Survey
Taught by
Matt Tearle
