On the robustness of learning in games with stochastically perturbed payoff observations
From MaRDI portal
Publication:2357809
Abstract: Motivated by the scarcity of accurate payoff feedback in practical applications of game theory, we examine a class of learning dynamics where players adjust their choices based on past payoff observations that are subject to noise and random disturbances. First, in the single-player case (corresponding to an agent trying to adapt to an arbitrarily changing environment), we show that the stochastic dynamics under study lead to no regret almost surely, irrespective of the noise level in the player's observations. In the multi-player case, we find that dominated strategies become extinct and we show that strict Nash equilibria are stochastically stable and attracting; conversely, if a state is stable or attracting with positive probability, then it is a Nash equilibrium. Finally, we provide an averaging principle for 2-player games, and we show that in zero-sum games with an interior equilibrium, time averages converge to Nash equilibrium for any noise level.
Recommendations
- Robustness of Learning in Games With Heterogeneous Players
- Learning dynamics in games with stochastic perturbations
- Learning in games with unstable equilibria
- Learning in perturbed asymmetric games
- Learning in games with risky payoffs
- Path to Stochastic Stability: Comparative Analysis of Stochastic Learning Dynamics in Games
- Stochastic Stability of Perturbed Learning Automata in Positive-Utility Games
- Stability of learning dynamics in two-agent, imperfect-information games
- Penalty-regulated dynamics and robust learning procedures in games
- Learning in games with continuous action sets and unknown payoff functions
Cites work
- ``Evolutionary selection dynamic in games: Convergence and limit properties
- A payoff-based learning procedure and its application to traffic games
- A useful extension of Itô's formula with applications to optimal stopping
- Consistency of vanishingly smooth fictitious play
- Convergence in models with bounded expected relative hazard rates
- Domination or equilibrium
- Evolutionarily stable strategies and game dynamics
- Evolutionary dynamics with aggregate shocks
- Evolutionary game dynamics
- Evolutionary Games and Population Dynamics
- Evolutionary Games in Economics
- Evolutionary stability in asymmetric games
- Exponential weight algorithm in continuous time
- scientific article; zbMATH DE number 5869530 (Why is no real title available?)
- scientific article; zbMATH DE number 3128728 (Why is no real title available?)
- scientific article; zbMATH DE number 1233801 (Why is no real title available?)
- scientific article; zbMATH DE number 1405930 (Why is no real title available?)
- scientific article; zbMATH DE number 3320765 (Why is no real title available?)
- Imitation dynamics with payoff shocks
- Individual Q-Learning in Normal Form Games
- Ito versus Stratonovich
- Learning in games via reinforcement and regularization
- Learning through reinforcement and replicator dynamics
- On the Global Convergence of Stochastic Fictitious Play
- ON THE REPLICATOR DYNAMICS BEHAVIOR UNDER STRATONOVICH TYPE RANDOM PERTURBATIONS
- Online learning and online convex optimization
- Optimal properties of stimulus-response learning models.
- Penalty-regulated dynamics and robust learning procedures in games
- Primal-dual subgradient methods for convex problems
- Projected Dynamical Systems in the Formulation, Stability Analysis, and Computation of Fixed-Demand Traffic Network Equilibria
- Rate control for communication networks: shadow prices, proportional fairness and stability
- Social Stability and Equilibrium
- Stability of regime-switching stochastic differential equations
- State space collapse and diffusion approximation for a network operating under a fair bandwidth sharing policy
- Stochastic Approximations and Differential Inclusions
- The emergence of rational behavior in the presence of stochastic perturbations
- The long-run behavior of the stochastic replicator dynamics
- The projection dynamic and the geometry of population games
- The weighted majority algorithm
- Time Average Replicator and Best-Reply Dynamics
- Time averages, recurrence and transience in the stochastic replicator dynamics
- Two Competing Models of How People Learn in Games
- When can the two-armed bandit algorithm be trusted?
Cited in
(21)- Riemannian game dynamics
- Learning in games with continuous action sets and unknown payoff functions
- Learning dynamics in games with stochastic perturbations
- Learning in nonatomic games. I: Finite action spaces and population games
- Imitation dynamics with payoff shocks
- Effects of noise on convergent game-learning dynamics
- Bush‐Mosteller learning for a zero-sum repeated game with random pay-offs
- Penalty-regulated dynamics and robust learning procedures in games
- On the convergence of gradient-like flows with noisy gradient input
- Independent Log-Linear Learning in Potential Games With Continuous Actions
- scientific article; zbMATH DE number 7042419 (Why is no real title available?)
- Corrections to “Stochastic Stability of Perturbed Learning Automata in Positive-Utility Games” [Nov 19 4454-4469]
- Stability of learning dynamics in two-agent, imperfect-information games
- Opinion dynamics with limited information
- Learning in rent-seeking contests with payoff risk and foregone payoff information
- No-regret learning for repeated non-cooperative games with lossy bandits
- scientific article; zbMATH DE number 7730611 (Why is no real title available?)
- Multiagent Online Learning in Time-Varying Games
- Nested replicator dynamics, nested logit choice, and similarity-based learning
- Stochastically perturbed payoff observations in an evolutionary game
- The emergence of rational behavior in the presence of stochastic perturbations
This page was built for publication: On the robustness of learning in games with stochastically perturbed payoff observations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2357809)
