Complex dynamics in learning complicated games
From MaRDI portal
Publication:5170992
DOI10.1073/PNAS.1109672110zbMATH Open1292.91033arXiv1109.4250OpenAlexW2128797809WikidataQ36567888 ScholiaQ36567888MaRDI QIDQ5170992FDOQ5170992
Authors: Tobias Galla, J. Doyne Farmer 
Publication date: 25 July 2014
Published in: Proceedings of the National Academy of Sciences (Search for Journal in Brave)
Abstract: Game theory is the standard tool used to model strategic interactions in evolutionary biology and social science. Traditional game theory studies the equilibria of simple games. But is traditional game theory applicable if the game is complicated, and if not, what is? We investigate this question here, defining a complicated game as one with many possible moves, and therefore many possible payoffs conditional on those moves. We investigate two-person games in which the players learn based on experience. By generating games at random we show that under some circumstances the strategies of the two players converge to fixed points, but under others they follow limit cycles or chaotic attractors. The dimension of the chaotic attractors can be very high, implying that the dynamics of the strategies are effectively random. In the chaotic regime the payoffs fluctuate intermittently, showing bursts of rapid change punctuated by periods of quiescence, similar to what is observed in fluid turbulence and financial markets. Our results suggest that such intermittency is a highly generic phenomenon, and 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
Full work available at URL: https://arxiv.org/abs/1109.4250
Recommendations
Dynamical systems in optimization and economics (37N40) 2-person games (91A05) Rationality and learning in game theory (91A26)
Cites Work
- Equilibrium points in n -person games
- Information Theory and Statistical Mechanics
- Evolutionary Games and Population Dynamics
- Experience-weighted Attraction Learning in Normal Form Games
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Heterogeneous beliefs and routes to chaos in a simple asset pricing model
- Asymptotic expected number of Nash equilibria of two-player normal form games
- Self-tuning experience weighted attraction learning in games
- Chaos in learning a simple two-person game
- Title not available (Why is that?)
Cited In (28)
- Title not available (Why is that?)
- On the expected number of internal equilibria in random evolutionary games with correlated payoff matrix
- Learning and sophistication in coordination games
- Assignment flows for data labeling on graphs: convergence and stability
- Coordination problems on networks revisited: statics and dynamics
- Chaos in learning a simple two-person game
- On equilibrium properties of the replicator-mutator equation in deterministic and random games
- Best-response dynamics in two-person random games with correlated payoffs
- Which types of learning make a simple game complex?
- Topology trivialization transition in random non-gradient autonomous ODEs on a sphere
- Learning process in public goods games
- Crises and collective socio-economic phenomena: simple models and challenges
- Pure Nash equilibria and best-response dynamics in random games
- Exploration-exploitation in multi-agent learning: catastrophe theory meets game theory
- Effect of information asymmetry in Cournot duopoly game with bounded rationality
- Memory-two strategies forming symmetric mutual reinforcement learning equilibrium in repeated prisoners' dilemma game
- Distribution of rare saddles in the p -spin energy landscape
- Title not available (Why is that?)
- Instabilities in large economies: aggregate volatility without idiosyncratic shocks
- Evolutionary multiplayer games
- Towards a taxonomy of learning dynamics in \(2\times 2\) games
- On the distribution of the number of internal equilibria in random evolutionary games
- Best-response dynamics, playing sequences, and convergence to equilibrium in random games
- Symmetric equilibrium of multi-agent reinforcement learning in repeated prisoner's dilemma
- Learning dynamics and norm psychology supports human cooperation in a large-scale prisoner's dilemma on networks
- Introspection dynamics in asymmetric multiplayer games
- Memory loss can prevent chaos in games dynamics
- Nonlinear analogue of the May-Wigner instability transition
This page was built for publication: Complex dynamics in learning complicated games
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5170992)
