Abstract | ||
---|---|---|
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. |
Year | Venue | Keywords |
---|---|---|
2007 | IJCAI | disparate state space,different state space,game player,general game,knowledge transfer,new game,game-tree lookahead structure,previous game,value-function transfer,feature-based value function transfer,different game,value function,state space,reinforcement learning |
Field | DocType | Citations |
Combinatorial game theory,Game mechanics,Computer science,Simulations and games in economics education,Repeated game,General game playing,Artificial intelligence,Screening game,Sequential game,Non-cooperative game,Machine learning | Conference | 45 |
PageRank | References | Authors |
2.95 | 5 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bikramjit Banerjee | 1 | 284 | 32.63 |
Peter Stone | 2 | 6878 | 688.60 |