AWESOME: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents

  title={AWESOME: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents},
  author={Vincent Conitzer and T. Sandholm},
  journal={Machine Learning},
  • Vincent Conitzer, T. Sandholm
  • Published 2006
  • Computer Science, Mathematics
  • Machine Learning
  • Two minimal requirements for a satisfactory multiagent learning algorithm are that it 1. learns to play optimally against stationary opponents and 2. converges to a Nash equilibrium in self-play. The previous algorithm that has come closest, WoLF-IGA, has been proven to have these two properties in 2-player 2-action (repeated) games—assuming that the opponent’s mixed strategy is observable. Another algorithm, ReDVaLeR (which was introduced after the algorithm described in this paper), achieves… CONTINUE READING
    270 Citations
    Unifying Convergence and No-Regret in Multiagent Learning
    • 1
    • Highly Influenced
    • PDF
    Efficiently detecting switches against non-stationary opponents
    • 21
    • PDF
    Generalized multiagent learning with performance bound
    • 16
    • Highly Influenced
    A Multiagent Reinforcement Learning Algorithm with Non-linear Dynamics
    • 74
    • Highly Influenced
    • PDF
    Learning against sequential opponents in repeated stochastic games
    • 14
    • PDF
    A general criterion and an algorithmic framework for learning in multi-agent systems
    • 52
    • PDF
    Towards a Fast Detection of Opponents in Repeated Stochastic Games
    • 16
    • PDF
    Sample Efficient Multiagent Learning in the Presence of Markovian Agents
    • D. Chakraborty
    • Computer Science
    • Studies in Computational Intelligence
    • 2014
    • 4
    • Highly Influenced
    • PDF
    Improving Convergence Rates in Multiagent Learning Through Experts and Adaptive Consultation
    • PDF


    Convergence and No-Regret in Multiagent Learning
    • 226
    • PDF
    New Criteria and a New Algorithm for Learning in Multi-Agent Systems
    • 122
    • PDF
    Performance Bounded Reinforcement Learning in Strategic Interactions
    • 46
    • PDF
    Multiagent reinforcement learning in the Iterated Prisoner's Dilemma.
    • 315
    • PDF
    Reinforcement Learning to Play an Optimal Nash Equilibrium in Team Markov Games
    • 225
    • PDF
    Fast Concurrent Reinforcement Learners
    • 38
    • PDF
    Multiagent learning using a variable learning rate
    • 732
    • Highly Influential
    • PDF
    Learning against opponents with bounded memory
    • 88
    • PDF