Tree [r4] /
 History



File Date Author Commit
 doc 2007-11-12 berger [r1] initial import 1.2 alpha
 src 2007-11-12 berger [r1] initial import 1.2 alpha
 AUTHORS 2007-11-12 berger [r1] initial import 1.2 alpha
 COPYING 2007-11-12 berger [r1] initial import 1.2 alpha
 ChangeLog 2007-11-12 berger [r1] initial import 1.2 alpha
 INSTALL 2007-11-12 berger [r1] initial import 1.2 alpha
 Makefile.am 2007-11-12 berger [r1] initial import 1.2 alpha
 NEWS 2007-11-13 ralfberger [r2]
 README 2007-11-17 ralfberger [r4] Anjuta-1 project file added
 RL++.prj 2007-11-17 ralfberger [r4] Anjuta-1 project file added
 TODO 2007-11-12 berger [r1] initial import 1.2 alpha
 autogen.sh 2007-11-12 berger [r1] initial import 1.2 alpha
 config.guess 2007-11-12 berger [r1] initial import 1.2 alpha
 config.h.in 2007-11-12 berger [r1] initial import 1.2 alpha
 config.sub 2007-11-12 berger [r1] initial import 1.2 alpha
 configure.in 2007-11-12 berger [r1] initial import 1.2 alpha
 copying 2007-11-12 berger [r1] initial import 1.2 alpha
 depcomp 2007-11-12 berger [r1] initial import 1.2 alpha
 install-sh 2007-11-12 berger [r1] initial import 1.2 alpha
 ltmain.sh 2007-11-16 ralfberger [r3]
 missing 2007-11-12 berger [r1] initial import 1.2 alpha
 mkinstalldirs 2007-11-12 berger [r1] initial import 1.2 alpha
 setup-gettext 2007-11-12 berger [r1] initial import 1.2 alpha
 stamp-h.in 2007-11-12 berger [r1] initial import 1.2 alpha

Read Me

License: GNU LESSER GENERAL PUBLIC LICENSE --> see COPYING for details!

See INSTALL for some basic information on how to install the library.

I apologize for the missing documentation, but I hope the examples will answer most of your possible questions.
In case of problems feel free to contact me at michaelgollin@users.sourceforge.net
and use the bugtracker and the forum on sf.net.

The package includes:
- all library source files for
  - reinforcement learning algorithms (Sarsa, Watkins Q-Learning, TD --> all with Eligibility Traces)
  - value functions (TileCoding (state and action based), LookupTable (state and action based) and Neuronal Network (only state based) )
  - utility classes
- 5 examples:
  - MountainCar with Actions (TileCoding), States (TileCoding and Neuronal Network)
  - Windy GridWorld Scenario with Actions and States (both Lookup Table)

Written and tested on:
  - Suse >= 8.2, Gentoo >= 2006
  - Kernel >= 2.4.20
  - gcc >= 3.3.1