Penalty-regulated dynamics and robust learning procedures in games
From MaRDI portal
Publication:3449451
Abstract: Starting from a heuristic learning scheme for N-person games, we derive a new class of continuous-time learning dynamics consisting of a replicator-like drift adjusted by a penalty term that renders the boundary of the game's strategy space repelling. These penalty-regulated dynamics are equivalent to players keeping an exponentially discounted aggregate of their on-going payoffs and then using a smooth best response to pick an action based on these performance scores. Owing to this inherent duality, the proposed dynamics satisfy a variant of the folk theorem of evolutionary game theory and they converge to (arbitrarily precise) approximations of Nash equilibria in potential games. Motivated by applications to traffic engineering, we exploit this duality further to design a discrete-time, payoff-based learning algorithm which retains these convergence properties and only requires players to observe their in-game payoffs: moreover, the algorithm remains robust in the presence of stochastic perturbations and observation errors, and it does not require any synchronization between players.
Recommendations
- On the robustness of learning in games with stochastically perturbed payoff observations
- A payoff-based learning procedure and its application to traffic games
- Learning in nonatomic games. I: Finite action spaces and population games
- Learning with minimal information in continuous games
- Learning dynamics in games with stochastic perturbations
Cites work
- scientific article; zbMATH DE number 1795161 (Why is no real title available?)
- A Simple Adaptive Procedure Leading to Correlated Equilibrium
- A payoff-based learning procedure and its application to traffic games
- A survey on networking games in telecommunications
- An adjusted payoff-based procedure for normal form games
- Asynchronous stochastic approximation with differential inclusions
- Attainability of boundary points under reinforcement learning
- Decentralized learning of Nash equilibria in multi-person stochastic games with incomplete information
- Evolutionary Games and Population Dynamics
- Evolutionary Selection in Normal-Form Games
- Evolutionary dynamics with aggregate shocks
- Exponential weight algorithm in continuous time
- Hessian Riemannian Gradient Flows in Convex Programming
- Higher order game dynamics
- Individual Q-Learning in Normal Form Games
- Inertial game dynamics and applications to constrained optimization
- Learning by trial and error
- Learning through reinforcement and replicator dynamics
- On the Global Convergence of Stochastic Fictitious Play
- Optimal properties of stimulus-response learning models.
- Potential games
- Quantal response equilibria for normal form games
- The emergence of rational behavior in the presence of stochastic perturbations
- Time Average Replicator and Best-Reply Dynamics
- Truncated stochastic approximation with moving bounds: convergence
- Two Competing Models of How People Learn in Games
- When can the two-armed bandit algorithm be trusted?
Cited in
(21)- A stochastic approximation algorithm for stochastic semidefinite programming
- Exploration-exploitation in multi-agent learning: catastrophe theory meets game theory
- Riemannian game dynamics
- Population games and discrete optimal transport
- Replicator dynamics: old and new
- Memory loss can prevent chaos in games dynamics
- Learning in games via reinforcement and regularization
- Nested replicator dynamics, nested logit choice, and similarity-based learning
- Bifurcation mechanism design -- from optimal flat taxes to better cancer treatments
- Continuous-time convergence rates in potential and monotone games
- On the stability of an adaptive learning dynamics in traffic games
- Inertial game dynamics and applications to constrained optimization
- Regularized Bayesian best response learning in finite games
- Performance of non-cooperative routing over parallel non-observable queues
- Robust power modulation for channel state information exchange
- On best-response dynamics in potential games
- On the robustness of learning in games with stochastically perturbed payoff observations
- Learning in games with continuous action sets and unknown payoff functions
- A unified stochastic approximation framework for learning in games
- No-regret algorithms in on-line learning, games and convex optimization
- Analysis of complex dynamics in different bargaining systems
This page was built for publication: Penalty-regulated dynamics and robust learning procedures in games
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3449451)
