Artificial Intelligence IV - Reinforcement Learning in Java
About this course
The course walks through the mathematical foundation of reinforcement learning using Markov Decision Processes, then shows how to solve them with value iteration, policy iteration, and Q‑learning. It demonstrates a model‑free Q‑learning approach, applies it to classic path‑finding problems, and extends the method with neural networks for function approximation. All examples and code are written in Java, so you can see the algorithms in action and adapt them to your own projects.
55/100
CourseAsk score
- What the provider tells you
- 31/45
- Who stands behind it
- 8/35
- How complete the listing is
- 16/20
Scores how much the provider publishes and who stands behind it — not how well it is taught.
What you'll learn
- Implement Markov Decision Processes and compute optimal policies with value and policy iteration
- Apply Q‑learning to solve reinforcement learning problems without a model
- Integrate neural networks with Q‑learning for function approximation
- Develop Java programs that use reinforcement learning for path‑finding tasks
Course objectives
- Explain the core concepts and mathematics behind reinforcement learning
- Compare model‑based and model‑free solution methods
- Write Java code that implements key RL algorithms
- Demonstrate how to train and evaluate Q‑learning agents
Price shown by Udemy — confirm on their site.
Enroll on UdemyYou'll be redirected to Udemy to complete enrollment.
- Listed & compared by CourseAsk
- English · 0
More courses like this
Compared on these lists
Where this course ranks against the alternatives.
Coursera