For my master study Agent Technology at the Utrecht University, I was part of a little group making a learning poker player:
RL Poker is a study project Java implementation of an e-soft on-policy Monte Carlo Texas Hold’em poker reinforcement learning algoritm with a feedforward neural network and backpropagation. It provides a graphical interface to monitor game rounds.
Have a look at the SourceForge project website. Code is available from SVN.