''SkyAI is a highly modularized Reinforcement Learning library for real/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 [#news]

:June 14, 2010|The development version has been released. You can [[browse code:http://skyai.git.sourceforge.net/]]. Please see also Installation Guide.

* Implemented Modules [#modules]

- Q(λ)-learning, Sarsa(λ)
- Fitted Q iteration
- LSPI (experimental)
- Logger modules
- Wire-fitting
- Grid action space
- DCOB, WF-DCOB

* Contents [#contents]

- [[Introduction]]
- [[License]]
- Source code:
-- [[Browse source code (Git Browse):http://skyai.git.sourceforge.net/]]
-- Git repository (read-only):
  git://skyai.git.sourceforge.net/gitroot/skyai/skyai
- Documentation
-- Installation Guide
-- read more...
- Developers
- Screenshots and Movies
- [[Documentation]]
-- [[Introduction>Documentation/Introduction]]
-- [[Installation Guide>Documentation/Installation Guide]]
-- [[read more...>Documentation]]
- [[Developers]]
- [[Demos]]: Screenshots and Movies


Front page   New List of pages Search Recent changes   Help   RSS of recent changes