Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2016 Nov 16;11(11):e0166708.
doi: 10.1371/journal.pone.0166708. eCollection 2016.

Melioration Learning in Two-Person Games

Johannes Zschache  1
Affiliations

Melioration Learning in Two-Person Games

Johannes Zschache. PLoS One. .

Abstract

Melioration learning is an empirically well-grounded model of reinforcement learning. By means of computer simulations, this paper derives predictions for several repeatedly played two-person games from this model. The results indicate a likely convergence to a pure Nash equilibrium of the game. If no pure equilibrium exists, the relative frequencies of choice may approach the predictions of the mixed Nash equilibrium. Yet in some games, no stable state is reached.

PubMed Disclaimer

Conflict of interest statement

The author has declared that no competing interests exist.

Figures

Fig 1
Fig 1. The situation of sequential decision-making.
Fig 2
Fig 2. A prisoner’s dilemma and simulation results.
Fig 3
Fig 3. The game “guess 23 of the average” and simulation results.
Fig 4
Fig 4. A game with three optimal Nash equilibria.
Fig 5
Fig 5. A coordination game and simulation results.
Fig 6
Fig 6. Relationship between the rewards of (B,B) and frequencies.
Fig 7
Fig 7. Relationship between non-equilibrium rewards and frequencies.
Fig 8
Fig 8. A “battle of the sexes” and a game of chicken.
Fig 9
Fig 9. A dispersion game and simulation results.
Fig 10
Fig 10. The game “matching pennies” and simulation results.
Fig 11
Fig 11. The game “rock-paper-scissors” and simulation results.
Fig 12
Fig 12. An example of the inspection game and simulation results.
Fig 13
Fig 13. The inspection game with low or high punishment.
Fig 14
Fig 14. Shapley’s game and simulation results.
See this image and copyright information in PMC

References

    1. Young HP. Strategic Learning and its Limits. New York: Oxford University Press; 2004. 10.1093/acprof:oso/9780199269181.001.0001 - DOI
    1. Hart S, Mas-Colell A. Uncoupled dynamics do not lead to Nash equilibrium. The American Economic Review. 2003;93(5):1830–1836. 10.1257/000282803322655581 - DOI
    1. Foster DP, Young HP. Regret testing: Learning to play Nash equilibrium without knowing you have an opponent. Theoretical Economics. 2006;1(3):341–367.
    1. Babichenko Y. Completely uncoupled dynamics and Nash equilibria. Games and Economic Behavior. 2012;76(1):1–14. 10.1016/j.geb.2012.06.004 - DOI
    1. Germano F, Lugosi G. Global Nash convergence of Foster and Young’s regret testing. Games and Economic Behavior. 2007;60(1):135–154.

LinkOut - more resources