Related Experiment Videos

Multiagent reinforcement learning in the Iterated Prisoner's Dilemma

T W Sandholm1, R H Crites

  • 1Computer Science Department, University of Massachusetts at Amherst 01003, USA.

Bio Systems
|January 1, 1996
PubMed
Summary

Reinforcement learning agents using Q-learning can play the Iterated Prisoner's Dilemma. Agents with longer histories and memory performed best against adaptive opponents, showing improved reinforcement learning strategies.

Related Concept Videos