Learning in Games via Reinforcement and Regularization
From MaRDI portal
Publication:2833105
DOI10.1287/moor.2016.0778zbMath1349.91063arXiv1407.6267OpenAlexW2254533881WikidataQ60142062 ScholiaQ60142062MaRDI QIDQ2833105
William H. Sandholm, Panayotis Mertikopoulos
Publication date: 16 November 2016
Published in: Mathematics of Operations Research (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1407.6267
regularizationreplicator dynamicspenalty functionsreinforcement learningBregman divergencedominated strategiesequilibrium stabilitytime averagesprojection dynamicsFenchel coupling
Convex programming (90C25) Rationality and learning in game theory (91A26) Evolutionary games (91A22)
Related Items (18)
On the robustness of learning in games with stochastically perturbed payoff observations ⋮ Replicator dynamics: old and new ⋮ Riemannian game dynamics ⋮ Evolutionary game theory: a renaissance ⋮ Inertial Game Dynamics and Applications to Constrained Optimization ⋮ Continuous-Time Convergence Rates in Potential and Monotone Games ⋮ Exploration-exploitation in multi-agent learning: catastrophe theory meets game theory ⋮ No-regret algorithms in on-line learning, games and convex optimization ⋮ A unified stochastic approximation framework for learning in games ⋮ Continuous time learning algorithms in optimization and game theory ⋮ On the Convergence of Gradient-Like Flows with Noisy Gradient Input ⋮ Learning in games with continuous action sets and unknown payoff functions ⋮ Population games and discrete optimal transport ⋮ Adaptive learning in large populations ⋮ Reinforcement with Fading Memories ⋮ On the uniqueness of quantal response equilibria and its application to network games ⋮ Tributes to Bill Sandholm ⋮ Learning in nonatomic games. I: Finite action spaces and population games
Cites Work
- Unnamed Item
- Unnamed Item
- Primal-dual subgradient methods for convex problems
- A continuous-time approach to online optimization
- Escort evolutionary game theory
- ``Evolutionary selection dynamic in games: Convergence and limit properties
- Adaptive dynamics and evolutionary stability
- Exponential weight algorithm in continuous time
- The emergence of rational behavior in the presence of stochastic perturbations
- A payoff-based learning procedure and its application to traffic games
- Domination or equilibrium
- Evolutionary stability in asymmetric games
- Learning, matching, and aggregation
- The weighted majority algorithm
- Learning through reinforcement and replicator dynamics
- Riemannian game dynamics
- On the convergence of reinforcement learning
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- Adaptive game playing using multiplicative weights
- A note on best response dynamics.
- Optimal properties of stimulus-response learning models.
- Quantal response equilibria for normal form games
- No-regret dynamics and fictitious play
- Possible generalization of Boltzmann-Gibbs statistics.
- Higher order game dynamics
- The projection dynamic and the geometry of population games
- The projection dynamic and the replicator dynamic
- Attainability of boundary points under reinforcement learning
- Perturbed variations of penalty function methods. Example: Projective SUMT
- Online Learning and Online Convex Optimization
- Time Average Replicator and Best-Reply Dynamics
- Inertial Game Dynamics and Applications to Constrained Optimization
- Social Stability and Equilibrium
- Penalty-Regulated Dynamics and Robust Learning Procedures in Games
- The Nonlinear Geometry of Linear Programming. I Affine and Projective Scaling Trajectories
- Evolutionary Games in Economics
- Free-Steering Relaxation Methods for Problems with Strictly Convex Costs and Linear Constraints
- Projected Dynamical Systems in the Formulation, Stability Analysis, and Computation of Fixed-Demand Traffic Network Equilibria
- Evolutionary Games and Population Dynamics
- Barrier Operators and Associated Gradient-Like Dynamical Systems for Constrained Minimization Problems
- A Simple Adaptive Procedure Leading to Correlated Equilibrium
- Hessian Riemannian Gradient Flows in Convex Programming
- Stochastic Approximations and Differential Inclusions
- Individual Q-Learning in Normal Form Games
- Two Competing Models of How People Learn in Games
- On the Global Convergence of Stochastic Fictitious Play
This page was built for publication: Learning in Games via Reinforcement and Regularization
