Verve is a library implementing general purpose reinforcement learning agents. It combines radial basis functions, temporal difference learning, planning, uncertainty estimations, and curiosity. It is intended to be an out-of-the-box solution for roboticists and game developers.


  • About - General info, features, limitations, license info, etc.
  • Gallery - Images and videos.
  • Downloads - Download the library and sample applications.
  • Documentation - API documentation, publications, etc.
  • Contact - Contact the developer.
home.txt · Last modified: 2008/11/03 04:32