Learning in a Black Box: Trial-and-Error in Voluntary Contribuitons Games

Many interactive environments can be represented as games, but they are so large and complex that individual players are in the dark about others' actions and the payoff structure.  This paper analyzes learning behavior in such 'black box' environments, where players' only source of information is their own history of actions taken and payoffs received.  Specifically we study voluntary contributions games.  We identify two robust features of the players' learning dynamics: search volatility and trend-following.  These features are clearly present when players have no information about the game; but also when players have full informaiton.  Convergence to Nash equilibrium occurs at about the same rate in both situations.