Multi agent reinforcement learning (MARL) is an interesting avenue to investigate human behavior and emergent group phenomena. Although recent years have brought advances in this field, significant results are still scarce.

MARL can be sub divided into three categories:

  • Cooperative setting
  • Competitive setting
  • Mixed setting
Single Agent Reinforcement Learning
Multi Agent Reinforcement Learning

Areas of significance

  • The sequence of the agents in a time cycle do matter. Agents can act (partially) simultaneous and/or (partially) sequentially
  • Non-stationary.
  • Function approximation
  • Stochastic gradient descent
  • Importance sampling
  • Mixed games can probably use the loss aversion model of Kahnemann and Tversky in the reward structure. This sheds likely new light on the zero-sum asymmetric reward intake.