Backgammon is a two-player, perfect information game of skill and luck. Its large branching factor (number of different position the game pieces can be in after each turn) means that it can't be solved by simply reasoning through all possible moves, and the uncertainty of dice rolls means that probabilities and contingencies must be factored into strategies.
Although TD-Gammon is one of the major successes in machine learning, it has not led to similar impressive breakthroughs in temporal difference We werelearning for other applications or even other games. Instead we apply simple hill-climbing in a relative fitness environment. These results and further analysis suggest of Tesauro's program had more to do with thethat the surprising success of the learning task and the dynamics of theco-evolutionary structure backgammon game itself. 1 INTRODUCTION It took great chutzpah for Gerald Tesauro to start wasting computer cycles on temporal of Backgammon (Tesauro, 1992). After all, the dream ofprogram play itself in the hopes computers mastering a domain by self-play or "introspection" had been around since the early days of AI, forming part of Samuel's checker player (Samuel, 1959) and used in Donald Michie's MENACE tictac-toe learner (Michie, 1961). However such self-conditioning or nonexistent internal representations, had generally beensystems, with weak of scale and abandoned by the field of AI.