Mean-Field Controls with Q-Learning for Cooperative MARL: Convergence and Complexity Analysis
From MaRDI portal
Publication:5018896
DOI10.1137/20M1360700zbMath1479.49088arXiv2002.04131OpenAlexW3208215078MaRDI QIDQ5018896
Xin Guo, Haotian Gu, Xiaoli Wei, Renyuan Xu
Publication date: 27 December 2021
Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2002.04131
cooperative gamesQ-learningmean-field controldynamic programming principlemulti-agent reinforcement learning
Noncooperative games (91A10) Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40) Mean field games and control (49N80)
Related Items
Unified reinforcement Q-learning for mean field game and control problems, Graphon mean-field control for cooperative multi-agent reinforcement learning, Model-free mean-field reinforcement learning: mean-field MDP and mean-field Q-learning, Reinforcement learning and stochastic optimisation, Exploratory LQG mean field games with entropy regularization
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Discrete time McKean-Vlasov control problem: a dynamic programming approach
- Lipschitz continuity of value functions in Markovian decision processes
- Mean field games
- Kernel-based reinforcement learning
- Variable resolution discretization in optimal control
- \({\mathcal Q}\)-learning
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- Viscosity solutions to parabolic master equations and McKean-Vlasov SDEs with closed-loop controls
- Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
- Risk-Sensitive Mean-Field Type Control Under Partial Observation
- Empirical Dynamic Programming
- A Stochastic Maximum Principle for Risk-Sensitive Mean-Field Type Control
- Learning in Mean-Field Games
- Approximate Markov-Nash Equilibria for Discrete-Time Risk-Sensitive Mean-Field Games
- A Hilbert Space Embedding for Distributions
- On the McKean-Vlasov Limit for Interacting Diffusions
- Markov--Nash Equilibria in Mean-Field Games with Discounted Cost
- On Choosing and Bounding Probability Metrics
- Discrete-time average-cost mean-field games on Polish spaces
- Robust mean field social control problems with applications in analysis of opinion dynamics
- Approximate Nash Equilibria in Partially Observed Stochastic Games with Mean-Field Interactions
- Kernel-based reinforcement learning in average-cost problems
- Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized $\varepsilon$-Nash Equilibria
- Probabilistic Theory of Mean Field Games with Applications I
- Probabilistic Theory of Mean Field Games with Applications II
- Control Techniques for Complex Networks
- Algorithms for optimization and stabilization of controlled Markov chains.
