Learning in games with continuous action sets and unknown payoff functions

2018/03/12 by Panayotis Mertikopoulos, Zhengyuan Zhou · 186 citations
Computer Science · Decision Sciences · Mathematics · #Action (physics) #Advanced Bandit Algorithms Research #Applied mathematics #Bounded function #Computer science #Convergence (economics) #Fictitious play #Game Theory and Applications #Mathematical analysis #Mathematical economics #Mathematical optimization #Mathematics #Nash equilibrium #Regret #Reinforcement Learning in Robotics #Sequence (biology) #Stability (learning theory) #Statistics #Stochastic game #Variance (accounting)

paper · open access · doi:10.1007/s10107-018-1254-8

published in Mathematical Programming 173(1-2), 465-507 (Springer Science+Business Media)

openalex publication_date 2018/03/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Cited by

• On the convergence of single-call stochastic extra-gradient methods
• Certifying Concavity and Monotonicity in Games via Sum-of-Squares Hierarchies
• Robust equilibria in continuous games: From strategic to dynamic robustness
• Multi-agent learning under uncertainty: Recurrence vs. concentration
• Adaptive extra-gradient methods for min-max optimization and games
• Second-Order Mirror Descent: Convergence in Games Beyond Averaging and Discounting
• Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium
• Stochastic Extragradient: General Analysis and Improved Rates
• Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information
• Convergence Analysis of Gradient-Based Learning with Non-Uniform Learning Rates in Non-Cooperative Multi-Agent Settings
• Game-Theoretic Multiagent Reinforcement Learning
• Finding a Multiple Follower Stackelberg Equilibrium: A Fully First-Order Method
• End-to-End Learning and Intervention in Games
• A Modular Algorithm for Non-Stationary Online Convex-Concave Optimization
• Invariant Risk Minimization Games
• Multi-Agent Online Optimization with Delays: Asynchronicity, Adaptivity, and Optimism
• No-regret learning and mixed Nash equilibria: They do not mix
• First- and Zeroth-Order Learning in Asynchronous Games
• Uncoupled Bandit Learning towards Rationalizability: Benchmarks, Barriers, and Algorithms
• No-regret Learning in Cournot Games
• No-regret distributed learning in subnetwork zero-sum games
• Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and Curvature
• Distributed stochastic optimization with large delays
• Efficient Decentralized Learning of Generalized Quantal Response Equilibrium
• Last-Iterate Convergence of No-Regret Learning for Equilibria in Bargaining Games
• The Confluence of Networks, Games and Learning
• Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games
• Pricing Mechanism for Resource Sustainability in Competitive Online Learning Multi-Agent Systems
• Agentic Markets: Game Dynamics and Equilibrium in Markets with Learning Agents
• The impact of uncertainty on regularized learning in games
• Asymmetric Perturbation in Solving Bilinear Saddle-Point Optimization
• Multi-Agent Reinforcement Learning in Cournot Games
• Solving Structured Hierarchical Games Using Differential Backward Induction
• On the convergence of mirror descent beyond stochastic convex programming
• On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems
• Hamiltonian of polymatrix zero-sum games
• Stable Opponent Shaping in Differentiable Games
• Algorithmic Pricing and Algorithmic Collusion
• Gradient-free Online Learning in Games with Delayed Rewards
• A Unified Variational Design of Predictive Mirror Descent in Convex Games under Stochastic Feedback