SkyAI is a highly modularized Reinforcement Learning library for real and simulation robots to learn behaviors. Our ultimate goal is to develop an artificial intelligence (AI) program with which the robots can learn to behave as their users wish.
News †
- December 6, 2010
- SkyAI is introduced in Humanoids2010. You can download the paper from here.
- September 22, 2010
- SkyAI is introduced in RSJ2010. You can download the paper (in Japanese) from here.
- June 14, 2010
- The development version has been released. You can browse code.
Implemented Modules †
- Q(λ)-learning, Sarsa(λ)
- Fitted Q iteration
- LSPI (experimental)
- Logger modules
- Wire-fitting
- Grid action space
- DCOB, WF-DCOB
Contents †