Continuous Strategy Replicator Dynamics for Multi--Agent Learning

Computer Science – Learning

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

12 pages, 15 figures, accepted for publication in JAAMAS

Scientific paper

10.1007/s10458-011-9181-6

The problem of multi-agent learning and adaptation has attracted a great deal of attention in recent years. It has been suggested that the dynamics of multi agent learning can be studied using replicator equations from population biology. Most existing studies so far have been limited to discrete strategy spaces with a small number of available actions. In many cases, however, the choices available to agents are better characterized by continuous spectra. This paper suggests a generalization of the replicator framework that allows to study the adaptive dynamics of Q-learning agents with continuous strategy spaces. Instead of probability vectors, agents strategies are now characterized by probability measures over continuous variables. As a result, the ordinary differential equations for the discrete case are replaced by a system of coupled integral--differential replicator equations that describe the mutual evolution of individual agent strategies. We derive a set of functional equations describing the steady state of the replicator dynamics, examine their solutions for several two-player games, and confirm our analytical results using simulations.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Continuous Strategy Replicator Dynamics for Multi--Agent Learning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Continuous Strategy Replicator Dynamics for Multi--Agent Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Continuous Strategy Replicator Dynamics for Multi--Agent Learning will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-442477

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.