Corpus ID: 3231252

Maintaining cooperation in complex social dilemmas using deep reinforcement learning

  title={Maintaining cooperation in complex social dilemmas using deep reinforcement learning},
  author={A. Lerer and Alexander Peysakhovich},
  • A. Lerer, Alexander Peysakhovich
  • Published 2017
  • Computer Science
  • ArXiv
  • Social dilemmas are situations where individuals face a temptation to increase their payoffs at a cost to total welfare. Building artificially intelligent agents that achieve good outcomes in these situations is important because many real world interactions include a tension between selfish interests and the welfare of others. We show how to modify modern reinforcement learning methods to construct agents that act in ways that are simple to understand, nice (begin by cooperating), provokable… CONTINUE READING
    71 Citations
    Consequentialist conditional cooperation in social dilemmas with imperfect information
    • 30
    • PDF
    Inducing Cooperative behaviour in Sequential-Social dilemmas through Multi-Agent Reinforcement Learning using Status-Quo Loss
    • Highly Influenced
    • PDF
    Learning Reciprocity in Complex Sequential Social Dilemmas
    • 11
    • Highly Influenced
    • PDF
    Prosocial learning agents solve generalized Stag Hunts better than selfish ones
    • 41
    • PDF
    Evolving intrinsic motivations for altruistic behavior
    • 20
    • PDF
    Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences
    • 1
    • PDF
    The Imitation Game: Learned Reciprocity in Markov games
    • 4
    • PDF
    Inequity aversion improves cooperation in intertemporal social dilemmas
    • 54
    • PDF


    Multi-agent Reinforcement Learning in Sequential Social Dilemmas
    • 277
    • PDF
    Multiagent reinforcement learning in the Iterated Prisoner's Dilemma.
    • 315
    • PDF
    Multiagent cooperation and competition with deep reinforcement learning
    • 290
    • PDF
    Social reward shaping in the prisoner's dilemma
    • 51
    • PDF
    Learning dynamics in social dilemmas
    • M. Macy, A. Flache
    • Sociology, Economics
    • Proceedings of the National Academy of Sciences of the United States of America
    • 2002
    • 444
    • PDF
    Learning with Opponent-Learning Awareness
    • 206
    • PDF
    Deep Reinforcement Learning from Self-Play in Imperfect-Information Games
    • 143
    • PDF
    A multi-agent reinforcement learning model of common-pool resource appropriation
    • 77
    • PDF
    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
    • 893
    • PDF