The existing reinforcement learning methods have been seriously suffering from the curse of dimension problem especially when they are applied to multiagent dynamic environments. ...
This paper extends the link between evolutionary game theory and multi-agent reinforcement learning to multistate games. In previous work, we introduced piecewise replicator dynam...
Differential games (DGs), considered as a typical model of game with continuous states and non-linear dynamics, play an important role in control and optimization. Finding optimal...
We address the problem of learning in repeated N-player (as opposed to 2-player) general-sum games. We describe an extension to existing criteria focusing explicitly on such setti...
This paper describes an algorithm, called CQ-learning, which learns to adapt the state representation for multi-agent systems in order to coordinate with other agents. We propose ...