Current

Intermediate

40% Off

Decision Making and Reinforcement Learning

Coursera · Columbia University · Updated March 2026

Platform rating

4.5/5

AI Tutor Rating

8.3/10

Duration

1-3 months

Classes

60

Learn decision-making frameworks and reinforcement learning from Columbia University including MDPs, deep RL, and simulations.

What you'll get

Build multi-agent reinforcement learning systems

Apply RL to decision-making problems

Implement deep RL algorithms from scratch

Course Curriculum

6 chapters

Fit

Best for

ML Engineers

Data Scientists

AI Researchers

Deep Learning Practitioners

Not ideal for

Learners seeking only entry-level overviews

Prerequisites & pricing

Prerequisites

Python, basic ML

Pricing

Subscription

Certification

Certificate

Growth Leverage: Completing this course opens doors to roles such as Reinforcement Learning Engineer, AI Research Scientist, or Machine Learning Engineer specializing in decision-making systems, significantly enhancing prospects for advanced positions in AI and ML. Additionally, it lays the foundation for certifications like the TensorFlow Developer Certificate.

Skills Value: Employers are willing to pay a premium, with salaries for reinforcement learning specialists reaching upwards of $150,000, due to high demand for experts who can implement and optimize deep RL algorithms to solve complex decision-making problems in industries like robotics and finance.

Reinforcement Learning

Decision Making

Deep RL

Simulations

ShareCompare

Add to StackGo to Course

Alternatives to Decision Making and Reinforcement Learning

Compare

Current

Simplified Artificial Intelligence (AI): What AI is, what it is NOT, and ...

Skillshare · Skillshare Instructor

4.5

8.4/10

Self-paced

But broadly speaking, in reinforcement learning is the ability to learn by exploration. You put an agent into an environment. And by exploring the environment ...

Skillshare Premium ($13.99/mo)

ViewAddCompare

Third methodology is reinforcement learning. It focuses on training models to make decisions through trial and error, receiving feedback from the environment ...

The model generates multiple candidate actions and deep reinforcement learning, RL is used to optimize a policy that selects actions from among the candidates.

Master reinforcement learning from University of Alberta covering MDPs, value functions, policy methods, and deep RL.