Reinforcement Learning

The Reinforcement Learning team applies RL to agent behavior, task optimization, and autonomous decision-making. Work spans from classic RL algorithms to modern approaches like RLHF and offline RL.

Getting Started

• Reinforcement Learning: An Introduction — by Richard S. Sutton and Andrew G. Barto. The canonical textbook on RL.
• Spinning Up in Deep RL — by OpenAI. A hands-on educational resource for learning deep reinforcement learning.
• Deep Reinforcement Learning — by Yuxi Li. A survey of deep RL algorithms and techniques.

Key Resources

Reserved for resources submitted by the team lead.

Tools & Repositories

Reserved for tools, repositories, datasets, workspaces, and operational references submitted by the team lead.

Related Curriculum

• AI/ML: Reinforcement Learning — core RL concepts in the curriculum
• Agent Systems: Planning and Reasoning — planning as an RL problem
• Agent Systems: Evaluating Agents — evaluation metrics relevant to RL-based agents