Learning to compete, compromise, and cooperate in repeated general-sum games

Learning algorithms often obtain relatively low average payoffs in repeated general-sum games between other learning agents due to a focus on myopic best-response and one-shot Nash equilibrium (NE) strategies. A less myopic approach places focus on NEs of the repeated game, which suggests that (at the least) a learning agent should possess two properties. First, an agent should never learn to play a strategy that produces average payoffs less than the minimax value of the game. Second, an agent should learn to cooperate/compromise when beneficial. No learning algorithm from the literature is known to possess both of these properties. We present a reinforcement learning algorithm (M-Qubed) that provably satisfies the first property and empirically displays (in self play) the second property in a wide range of games.

• Type: Conference
• Year: 2005
• Where: ICML
• Authors: Jacob W. Crandall, Michael A. Goodrich
• Keywords: ICML 2005, Low Average Payoffs, Machine Learning, Myopic Approach Places, Reinforcement Learning Algorithm