Sciweavers

Share
ATAL
2003
Springer

A selection-mutation model for q-learning in multi-agent systems

9 years 3 months ago
A selection-mutation model for q-learning in multi-agent systems
Although well understood in the single-agent framework, the use of traditional reinforcement learning (RL) algorithms in multi-agent systems (MAS) is not always justified. The feedback an agent experiences in a MAS, is usually influenced by the other agents present in the system. Multi agent environments are therefore non-stationary and convergence and optimality guarantees of RL algorithms are lost. To better understand the dynamics of traditional RL algorithms we analyze the learning process in terms of evolutionary dynamics. More specifically we show how the Replicator Dynamics (RD) can be used as a model for Q-learning in games. The dynamical equations of Q-learning are derived and illustrated by some well chosen experiments. Both reveal an interesting connection between the exploitationexploration scheme from RL and the selection-mutation mechanisms from evolutionary game theory. Categories and Subject Descriptors I.2 [Artificial Intelligence]: Learning General Terms Theory, ...
Karl Tuyls, Katja Verbeeck, Tom Lenaerts
Added 06 Jul 2010
Updated 06 Jul 2010
Type Conference
Year 2003
Where ATAL
Authors Karl Tuyls, Katja Verbeeck, Tom Lenaerts
Comments (0)
books