Learning Models of Intelligent Agents

David Carmel and Shaul Markovitch. Learning Models of Intelligent Agents. In Proceedings of the Thirteenth National Conference on Artificial Intelligence, pages 62-67, Portland, Oregon, 1996.

Abstract

Agents that operate in a multi-agent system need an efficient strategy to handle their encounters with other agents involved. Searching for an optimal interactive strategy is a hard problem because it depends mostly on the behavior of the others. In this work, interaction among agents is represented as a repeated two-player game, where the agents' objective is to look for a strategy that maximizes their expected sum of rewards in the game. We assume that agents' strategies can be modeled as finite automata. A model-based approach is presented as a possible method for learning an effective interactive strategy. First, we describe how an agent should find an optimal strategy against a given model. Second, we present an unsupervised algorithm that infers a model of the opponent's automaton from its input/output behavior. A set of experiments that show the potential merit of the algorithm is reported as well.

Keywords: Opponent Modeling, Repeated Games, Multi-Agent Systems, Learning DFA

Online version:

Bibtex entry:

 

@inproceedings{Carmel:1996:LMIa,
  Author =      {David Carmel and Shaul Markovitch},
  Title =       {Learning Models of Intelligent Agents},
  Year =        {1996},
  Booktitle =   {Proceedings of the Thirteenth National Conference on Artificial Intelligence},
  Pages =       {62--67},
  Keywords =    {Opponent Modeling, Repeated Games, Multi-Agent Systems, Learning DFA},
  Address =     {Portland, Oregon},
  Url =         {http://www.cs.technion.ac.il/~shaulm/papers/pdf/Carmel-Markovitch-OMM-aaai1996.p
            df},
  Abstract =    {Agents that operate in a multi-agent system need an efficient strategy to handle
             their encounters with other agents involved. Searching for an optimal
             interactive strategy is a hard problem because it depends mostly on the
             behavior of the others. In this work, interaction among agents is represented
             as a repeated two-player game, where the agents' objective is to look for a
             strategy that maximizes their expected sum of rewards in the game. We assume
             that agents' strategies can be modeled as finite automata. A model-based
             approach is presented as a possible method for learning an effective
             interactive strategy. First, we describe how an agent should find an optimal
             strategy against a given model. Second, we present an unsupervised algorithm
             that infers a model of the opponent's automaton from its input/output behavior.
             A set of experiments that show the potential merit of the algorithm is reported
             as well.}
}