The prevalence of chaotic dynamics in games with many players

@article{Sanders2018ThePO,
  title={The prevalence of chaotic dynamics in games with many players},
  author={James B. T. Sanders and J. Doyne Farmer and Tobias Galla},
  journal={Scientific Reports},
  year={2018},
  volume={8}
}
We study adaptive learning in a typical p-player game. The payoffs of the games are randomly generated and then held fixed. The strategies of the players evolve through time as the players learn. The trajectories in the strategy space display a range of qualitatively different behaviours, with attractors that include unique fixed points, multiple fixed points, limit cycles and chaos. In the limit where the game is complicated, in the sense that the players can take many possible actions, we use… 

Deciphering chaos in evolutionary games.

TLDR
This work constructs a game-theoretic solution that is realized as the chaotic outcomes in the selection monotone game dynamic that is optimized over the generations of the evolutionary process.

Quasi-stationary states of game-driven systems: A dynamical approach.

TLDR
This work demonstrates that a model of two antagonistic populations, which are playing a game with stationary or periodically varying payoffs, exhibits metastable dynamics that is reducible neither to an immediate transition to a fixation nor to the mean-field picture.

Unpredictable dynamics in congestion games: memory loss can prevent chaos

We study the dynamics of simple congestion games with two resources where a continuum of agents behaves according to a version of Experience-Weighted Attraction (EWA) algorithm. The dynamics is

UNPREDICTABILITY IN CONGESTION GAMES: MEMORY LOSS CAN PREVENT CHAOS

We study the dynamics of simple congestion games with two resources where a continuum of agents behaves according to a version of Experience-Weighted Attraction (EWA) algorithm. The dynamics is

Poincaré-Bendixson Limit Sets in Multi-Agent Learning

TLDR
This paper shows that behaviors consistent with the PoincaréBendixson theorem (limit cycles, but no chaotic attractor) follows purely based on the topological structure of the interaction graph, even for high-dimensional settings with arbitrary number of players and arbitrary payoff matrices.

Constants of Motion: The Antidote to Chaos in Optimization and Game Dynamics

TLDR
It is shown how proving the existence of invariant functions, i.e., constant of motions, is a fundamental contribution in this direction and establish a plethora of such positive results both in optimization as well as in game settings.

Best reply structure and equilibrium convergence in generic games

TLDR
It is shown that best reply cycles, basic topological structures in games, predict nonconvergence of six well-known learning algorithms that are used in biology or have support from experiments with human players.

The route to chaos in routing games: When is price of anarchy too optimistic?

TLDR
A stress test for classic routing games with arbitrarily many strategies, polynomial cost functions, non-atomic as well as atomic routing games and heteregenous users shows that every system has a carrying capacity, above which it becomes unstable.

Nash, Conley, and Computation: Impossibility and Incompleteness in Game Dynamics

Under what conditions do the behaviors of players, who play a game repeatedly, converge to a Nash equilibrium? If one assumes that the players’ behavior is a discrete-time or continuous-time rule

No-Regret Learning in Games is Turing Complete

TLDR
This paper proves Turing completeness of the replicator dynamic on matrix games, one of the simplest possible settings, and implies the undecicability of reachability problems for learning algorithms in games, a special case of which is determining equilibrium convergence.

References

SHOWING 1-10 OF 33 REFERENCES

Complex dynamics in learning complicated games

TLDR
This work investigates two-person games in which the players learn based on a type of reinforcement learning called experience-weighted attraction (EWA), and suggests that there is a large parameter regime for which complicated strategic interactions generate inherently unpredictable behavior that is best described in the language of dynamical systems theory.

Chaos in learning a simple two-person game

TLDR
That chaos can occur in learning a simple game indicates one should use caution in assuming real people will learn to play a game according to a Nash equilibrium strategy, as it provides an important self-consistency condition for determining when players will learning to behave as though they were fully rational.

Best reply structure and equilibrium convergence in generic games

TLDR
It is shown that best reply cycles, basic topological structures in games, predict nonconvergence of six well-known learning algorithms that are used in biology or have support from experiments with human players.

Entropy and typical properties of Nash equilibria in two-player games

We use techniques from the statistical mechanics of disordered systems to analyse the properties of Nash equilibria of bimatrix games with large random payoff matrices. By means of an annealed bound,

The Theory of Learning in Games

Phase transition and 1/f noise in a game dynamical model.

TLDR
An exact steady-state solution is presented as a function of the population's cooperation pressure u when the number of species is large and the interactions are taken as random, and when u is lowered to a critical value u c, the solution becomes unstable.

Random replicators with asymmetric couplings

Systems of interacting random replicators are studied using generating functional techniques. While replica analyses of such models are limited to systems with symmetric couplings, dynamical

Equilibrium Points in N-Person Games.

  • J. Nash
  • Economics
    Proceedings of the National Academy of Sciences of the United States of America
  • 1950
One may define a concept of an n -person game in which each player has a finite set of pure strategies and in which a definite set of payments to the n players corresponds to each n -tuple of pure

Random replicators with high-order interactions

TLDR
It is found that for p>2 there is a threshold value which gives a lower bound to the concentration of the surviving species, preventing the existence of rare species and, consequently, increasing the robustness of the ecosystem to external perturbations.