Abstract | ||
---|---|---|
The application of reinforcement learning algorithms to multiagent
domains may cause complex non-convergent dynamics. The replicator
dynamics, commonly used in evolutionary game theory, proved to be
effective for modeling the learning dynamics in normal form games.
Nonetheless, it is often interesting to study the robustness of the
learning dynamics when either learning or structural
parameters are perturbed. This is equivalent to unfold the catalog
of learning dynamical scenarios that arise for all possible parameter
settings which, unfortunately, cannot be obtained through ``brute
force'' simulation of the replicator dynamics. The analysis of bifurcations,
i.e., critical parameter combinations at which the learning behavior
undergoes radical changes, is mandatory.
In this work, we introduce a one-parameter bifurcation analysis of
the Selten's Horse game in which the learning process exhibits a
set of complex dynamical scenarios even for relatively small perturbations
on payoffs. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-77949-0_10 | Autonomous Agents and Multi-Agent Systems |
Keywords | Field | DocType |
critical parameter combination,complex non-convergent dynamic,dynamical scenario,replicator dynamic,normal form game,horse game,possible parameter setting,one-parameter bifurcation analysis,complex dynamical scenario,evolutionary game theory | Bifurcation analysis,Computer science,Replicator equation,Theoretical computer science,Robustness (computer science),Brute force,Artificial intelligence,Evolutionary game theory,Nash equilibrium,Hopf bifurcation,Reinforcement learning | Conference |
ISBN | Citations | PageRank |
3-540-77947-7 | 0 | 0.34 |
References | Authors | |
4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alessandro Lazaric | 1 | 518 | 48.19 |
Enrique Munoz de Cote | 2 | 174 | 20.97 |
Fabio Dercole | 3 | 47 | 14.32 |
Marcello Restelli | 4 | 416 | 61.31 |