Offline Reinforcement Learning Courses and Certifications

Montreal Robotics

RobotLearning: Scaling Offline Reinforcement Learning

Explore offline reinforcement learning techniques for robots, including trajectory stitching, model-based approaches, Decision Transformers, and methods for integrating offline data into training pipelines.

• YouTube
• 1 hour 47 minutes
• Self-Paced
• Free Video

Stanford Seminar - Decision Transformer: Reinforcement Learning via Sequence Modeling

2 ratings

Decision Transformer treats reinforcement learning as conditional sequence modeling, generating actions from desired returns, past states, and actions.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Edan Meyer

Learning From Passive Data Explained

Explains an offline reinforcement learning algorithm that uses successor features to learn from passive data without interacting with the environment.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Stanford CS234 - Reinforcement Learning - Spring 2024

Master reinforcement learning fundamentals through Stanford's comprehensive program covering MDP planning, policy evaluation, Q-learning, exploration strategies, and deep RL applications.

• YouTube
• 20 hours 11 minutes
• Self-Paced
• Free Video