 |
Software available for download under
various open source licences:
The Pinball Domain
The
Pinball domain is
a fairly challenging 4-dimensional continuous and dynamic reinforcement
learning
domain. The goal is to maneuver the blue ball into the red hole, while
avoiding (or using, since the ball is dynamic and collisions are
elastic) the obstacles. The dynamics of the ball and the presence of
obstacles result in a domain with sharp discontinuities, and the
location and shape of the obstacles can be specified so you can make
the domain as hard or as easy as you want.
The source code is in Java, and includes full documentation,
an
RL-Glue interface, and GUI
programs for editing obstacle
configurations, viewing saved trajectories, etc.
(GPL)
The Fourier Basis
I have contributed source code for an
RL-Glue-compatible
epsilon-greedy Sarsa(λ) agent that
uses the Fourier Basis to the RL-Library project.
The source
code and project summary are available on the
RL Library community wiki.
The code is in Java and is fully documented.
(Apache License)
The Fourier Basis is described in:
|
| |
