Main Page

From RL-Library

Jump to: navigation, search

The mission of the Reinforcement-Learning Library (RL-Library) is to create a centralized place for the reinforcement-learning community to share their RL-Glue compatible software projects.

The RL-Library serves two distinct needs. First, to provide standardized, trusted implementations of agents and environments from the reinforcement-learning literature. Second, as a repository for other RL-Glue compatible software and tools, including "up and coming" agents and environments.

About the RL-Library

RL-Library is part of the RL-Community family of websites and projects.

The RL-Library is not just about what a couple people in an ivory tower think the standards should be. It is a true community effort, and the direction of the RL-Library should be driven by the community's needs and interests. The power of library is what it can become, for all of us. If you disagree with what you see here, join the rl-library mailing list and start a conversation!

The RL-Library currently has 11 environments, 3 agents, 2 experiments and 4 tutorials!

The RL-Library was created to aid teaching and research. The library provides a variety of learning algorithms and problems for empirical research. The library is also a useful resource for creating assignments and course projects.

The RL-Library continuously being improved. If you'd like to take responsibility for any of the projects in the RL-Library and update their pages, please contact btanner@rl-community.org.

RL-Glue 1.x and 2.x compatible code

Looking for the RL-Glue 1.0 and 2.0 compatible code? Check out the old RL-Library website: http://rlai.cs.ualberta.ca/RLR/oldIndex.html

Personal tools