Skip to main content

and
  1. Chapter and Conference Paper

    Analyzing Multi-agent Reinforcement Learning Using Evolutionary Dynamics

    In this paper, we show how the dynamics of Q-learning can be visualized and analyzed from a perspective of Evolutionary Dynamics (ED). More specifically, we show how ED can be used as a model for Q-learning in...

    Pieter Jan’t Hoen, Karl Tuyls in Machine Learning: ECML 2004 (2004)

  2. Chapter and Conference Paper

    COllective INtelligence with Sequences of Actions

    The design of a Multi-Agent System (MAS) to perform well on a collective task is non-trivial. Straightforward application of learning in a MAS can lead to sub optimal solutions as agents compete or interfere. ...

    Pieter Jan ’t Hoen, Sander M. Bohte in Machine Learning: ECML 2003 (2003)