Corpus ID: 83458767

Learning Reciprocity in Complex Sequential Social Dilemmas

@article{Eccles2019LearningRI,
  title={Learning Reciprocity in Complex Sequential Social Dilemmas},
  author={Tom Eccles and E. Hughes and J{\'a}nos Kram{\'a}r and S. Wheelwright and Joel Z. Leibo},
  journal={ArXiv},
  year={2019},
  volume={abs/1903.08082}
}
  • Tom Eccles, E. Hughes, +2 authors Joel Z. Leibo
  • Published 2019
  • Computer Science
  • ArXiv
  • Reciprocity is an important feature of human social interaction and underpins our cooperative nature. What is more, simple forms of reciprocity have proved remarkably resilient in matrix game social dilemmas. Most famously, the tit-for-tat strategy performs very well in tournaments of Prisoner's Dilemma. Unfortunately this strategy is not readily applicable to the real world, in which options to cooperate or defect are temporally and spatially extended. Here, we present a general online… CONTINUE READING
    12 Citations

    Figures, Tables, and Topics from this paper.

    Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences
    Obedience-based Multi-Agent Cooperation for Sequential Social Dilemmas
    • 1
    • Highly Influenced
    Reward Redistribution Mechanisms in Multi-agent Reinforcement Learning
    Study on Modelling Human Behavior in Cooperative Games
    Learning to Incentivize Other Learning Agents
    • 1
    • PDF
    Learning to Communicate Implicitly by Actions
    • 4
    • PDF

    References

    SHOWING 1-10 OF 63 REFERENCES
    Consequentialist conditional cooperation in social dilemmas with imperfect information
    • 28
    • Highly Influential
    • PDF
    Inequity aversion resolves intertemporal social dilemmas
    • 15
    Maintaining cooperation in complex social dilemmas using deep reinforcement learning
    • 68
    • Highly Influential
    • PDF
    A multi-agent reinforcement learning model of common-pool resource appropriation
    • 72
    • PDF
    Mistakes allow evolutionary stability in the repeated prisoner's dilemma game.
    • R. Boyd
    • Biology, Medicine
    • Journal of theoretical biology
    • 1989
    • 208
    • PDF
    A strategy of win-stay, lose-shift that outperforms tit-for-tat in the Prisoner's Dilemma game
    • 1,379
    • PDF
    Emergence of Norms through Social Learning
    • 284
    • PDF
    Indirect reciprocity in asymmetric interactions: when apparent altruism facilitates profitable exploitation
    • 8
    • PDF
    When is tit-for-tat unbeatable?
    • 17
    • PDF