Towards a pareto-optimal solution in general-sum games

@inproceedings{Sen2003TowardsAP,
  title={Towards a pareto-optimal solution in general-sum games},
  author={Sandip Sen and St{\'e}phane Airiau and Rajatish Mukherjee},
  booktitle={AAMAS},
  year={2003}
}
Multiagent learning literature has investigated iterated two-player games to develop mechanisms that allow agents to learn to converge on Nash Equilibrium strategy profiles. Such equilibrium configuration implies that there is no motivation for one player to change its strategy if the other does not. Often, in general sum games, a higher payoff can be obtained by both players if one chooses not to respond optimally to the other player. By developing mutual trust, agents can avoid iterated best… CONTINUE READING
Highly Cited
This paper has 43 citations. REVIEW CITATIONS
29 Citations
2 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-2 of 2 references

Q-learning

  • C.J.C.H. Watkins, P. D. Dayan
  • Machine Learning, 3:279 – 292
  • 1992
Highly Influential
7 Excerpts

Similar Papers

Loading similar papers…