Sökning: "Anna Dollbo"

Hittade 1 uppsats innehållade orden Anna Dollbo.

  1. 1. MIXED MEMORY Q-LEARNER An adaptive reinforcement learning algorithm for the Iterated Prisoner’s Dilemma

    Kandidat-uppsats, Institutionen för tillämpad informationsteknologi

    Författare :Anna Dollbo; [2021-09-21]
    Nyckelord :Machine learning; reinforcement learning; game theory; iterated prisoner’s dilemma; state representation; Q-learning;

    Sammanfattning : The success of future societies is likely to depend on cooperative interactionsbetween humans and artificial agents. As such, it is important to investigate howmachines can learn to cooperate. LÄS MER