We present a reinforcement learning game player that can interact with a General Game Playing system and transfer knowledge learned in one game to expedite learning in many other games. We use the technique of value-function transfer where general features are extracted from the state space of a previous game and matched with the completely different state space of a new game. To capture the underlying similarity of vastly disparate state spaces arising from different games, we use a game-tree lookahead structure for features. We show that such feature-based value function transfer learns superior policies faster than a reinforcement learning agent that does not use knowledge transfer. Furthermore, knowledge transfer using lookahead features can capture opponent-specific value-functions, i.e. can exploit an opponent's weaknesses to learn faster than a reinforcement learner that uses lookahead with minimax (pessimistic) search against the same opponent.

PDF, PS, HTML

In The 20th International Joint Conference on Artificial Intelligence, 672-677, January 2007.

@InProceedings{IJCAI07-bikram, title={General Game Learning using Knowledge Transfer}, author={Bikramjit Banerjee and Peter Stone}, booktitle={The 20th International Joint Conference on Artificial Intelligence}, month={January}, pages={672-677}, url="http://nn.cs.utexas.edu/?IJCAI07-bikram", year={2007} }