Reinforcement Learning Courses and Certifications

University of Alberta;  Alberta Machine Intelligence Institute

Fundamentals of Reinforcement Learning

25 ratings

Reinforcement Learning is a subfield of Machine Learning, but is also a general purpose formalism for automated decision-making and AI. This course introduces you to statistical learning techniques where an agent explicitly takes actions and interacts wi…

• Coursera
• 5 weeks, 3 hours a week
• Self-Paced
• Paid Course

• Best of All Time

University of Alberta;  Alberta Machine Intelligence Institute

A Complete Reinforcement Learning System (Capstone)

28 ratings

Build a complete reinforcement learning system: formalize a word problem as an MDP, implement an Expected Sarsa or Q-learning agent with neural networks and RMSProp, then run a parameter study.

• Coursera
• 6 weeks, 3 hours a week
• Self-Paced
• Paid Course

University of Alberta;  Alberta Machine Intelligence Institute

Sample-based Learning Methods

44 ratings

Learn near-optimal policies from trial-and-error experience: implement Monte Carlo prediction and control, TD learning, Expected Sarsa, Q-learning, and the Dyna model-based architecture.

• Coursera
• 5 weeks, 4 hours a week
• Self-Paced
• Paid Course

Reinforcement Learning with Gymnasium in Python

764 ratings at DataCamp

Discover the World of Reinforcement Learning Embark on an exhilarating exploration of Reinforcement Learning (RL), a pivotal branch of machine learning.

• DataCamp
• 4 hours
• Self-Paced
• Free Trial Available

University of Alberta;  Alberta Machine Intelligence Institute

Prediction and Control with Function Approximation

24 ratings

Scale reinforcement learning to infinite state spaces: implement TD, expected Sarsa, Q-learning and Actor-Critic with tile-coding and neural network function approximation.

• Coursera
• 5 weeks, 4 hours a week
• Self-Paced
• Paid Course

Reinforcement Learning in Python

Master the fundamentals of reinforcement learning (RL) and discover how to build models to navigate complex environments often found in robotics and video games.

• DataCamp
• 12 hours
• Self-Paced
• Free Trial Available

Artificial Intelligence: Reinforcement Learning in Python

10817 ratings at Udemy

Complete guide to Reinforcement Learning, with Stock Trading and Online Advertising Applications

• Udemy
• 14 hours 43 minutes
• Self-Paced
• Paid Course

Career Certificate

Playing Games with Reinforcement Learning

Build intelligent agents that learn to navigate complex environments through reinforcement learning and Q-learning.

• CodeSignal
• 5 hours
• Self-Paced
• Free Certificate
• 4 courses

University of Alberta;  Alberta Machine Intelligence Institute Career Certificate

Reinforcement Learning

3599 ratings at Coursera

Implement a complete reinforcement learning solution end to end, covering RL fundamentals, sample-based learning methods, and prediction and control with function approximation.

• Coursera
• 8 weeks, 10 hours a week
• Self-Paced
• Paid Course
• 4 courses

Decision Making and Reinforcement Learning

25 ratings at Coursera

Model sequential decisions and implement RL algorithms: multi-armed bandits, MDPs and POMDPs, value and policy iteration, Monte Carlo control, SARSA, Q-learning and n-step TD.

• Coursera
• 8 weeks, 6 hours a week
• Self-Paced
• Paid Course

New York Institute of Finance;  Google Cloud

Reinforcement Learning for Trading Strategies

251 ratings at Coursera

Build trading strategies with reinforcement learning: distinguish actor-based from value-based policies, combine RL with neural networks and LSTMs, and train models using AutoML.

• Coursera
• 3 weeks, 4 hours a week
• Self-Paced
• Paid Course

Reinforcement Learning in Finance

134 ratings at Coursera

Apply reinforcement learning to finance: model option pricing as an MDP, compare dynamic programming and Q-learning, and use inverse RL for portfolio stock trading.

• Coursera
• 4 weeks, 4 hours a week
• Self-Paced
• Paid Course

Career Certificate

Foundations of Reinforcement Learning

5 ratings at Coursera

Learn reinforcement learning end to end: Markov decision processes, value and policy iteration, Q-learning, Deep Q-Networks, PPO, DDPG, SAC, reward shaping, and inverse reinforcement learning.

• Coursera
• 4 weeks, 10 hours a week
• Self-Paced
• Paid Course
• 3 courses

Mastering Classic Reinforcement Learning Algorithms

Formulate decisions as finite Markov decision processes and solve them with value iteration, policy iteration, bandits, Monte Carlo methods, temporal-difference learning, SARSA, and Q-learning.

• Coursera
• 5 weeks, 3 hours a week
• Self-Paced
• Paid Course

Overview of Advanced Methods of Reinforcement Learning in Finance

86 ratings at Coursera

Connect reinforcement learning to Black-Scholes-Merton option pricing and physics, use inverse reinforcement learning for market impact, and apply both to high-frequency trading, cryptocurrencies, and peer-to-peer lending.

• Coursera
• 4 weeks, 3 hours a week
• Self-Paced
• Paid Course