Gradient Descent for Symmetric and Asymmetric Multiagent Reinforcement Learning

Ville Könönen

    Research output: Contribution to journalArticleScientificpeer-review

    10 Citations (Scopus)
    Original languageEnglish
    Pages (from-to)17-30
    JournalWeb Intelligence and Agent Systems: An International Journal (WIAS)
    Publication statusPublished - 2005
    MoE publication typeA1 Journal article-refereed


    • Markov games
    • multiagent reinforcement learning
    • Nash equilibrium
    • Stackelberg equilibrium
    • value function approximation

    Cite this