Learning to Play Games in Extensive Form by Valuation

Game theoretic models of learning which are based on the strategic form of the game cannot explain learning in games with large extensive form. We study learning in such games by using valuation of moves. A valuation for a player is a numeric assessment of her moves that purports to reflect their desirability. We consider a myopic player, who chooses moves with the highest valuation. Each time the game is played, the player revises her valuation by assigning the payoff obtained in the play to each of the moves she has made. We show for a repeated win

• Type: Journal
• Year: 2002
• Where: CORR
• Authors: Philippe Jehiel, Dov Samet
• Keywords: CORR 2002, Education, Game, Game Theoretic Models, Large Extensive Form