RLE-Foundation/RLeXplore
A modularized Python toolkit providing standardized implementations of intrinsic reward exploration algorithms for reinforcement learning research.
Not currently ranked — collecting fresh signals.
star history
RLeXplore provides eight representative intrinsic reward algorithms for reinforcement learning, including count-based methods (PseudoCounts, RND, E3B), curiosity-driven approaches (ICM, Disagreement, RIDE), and memory-based techniques. The toolkit offers a unified workflow for constructing, computing, and optimizing intrinsic reward modules to enable standardized comparison of exploration strategies across different RL implementations.
Frequently asked
- What is RLE-Foundation/RLeXplore?
- A modularized Python toolkit providing standardized implementations of intrinsic reward exploration algorithms for reinforcement learning research.
- Is RLeXplore open source?
- Yes — RLE-Foundation/RLeXplore is open source, released under the MIT license.
- What language is RLeXplore written in?
- RLE-Foundation/RLeXplore is primarily written in Jupyter Notebook.
- How popular is RLeXplore?
- RLE-Foundation/RLeXplore has 465 stars on GitHub.
- Where can I find RLeXplore?
- RLE-Foundation/RLeXplore is on GitHub at https://github.com/RLE-Foundation/RLeXplore.