Buchumschlag

Accelerated Multi-Time-Scale Stochastic Approximation: Optimal Complexity and Applications in Reinforcement Learning and Multi-Agent Games

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zeng, Sihan, Doan, Thinh T.
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Optimization and Control
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Fast Two-Time-Scale Stochastic Gradient Method with Applications in Reinforcement Learning
von: Zeng, Sihan, et al.
Veröffentlicht: (2024)

A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning
von: Zeng, Sihan, et al.
Veröffentlicht: (2021)

Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning
von: Zeng, Sihan, et al.
Veröffentlicht: (2024)

Fast Nonlinear Two-Time-Scale Stochastic Approximation: Achieving $O(1/k)$ Finite-Sample Complexity
von: Doan, Thinh T.
Veröffentlicht: (2024)

Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes
von: Zeng, Sihan, et al.
Veröffentlicht: (2021)

Resilient Two-Time-Scale Local Stochastic Gradient Descent for Byzantine Federated Learning
von: Dutta, Amit, et al.
Veröffentlicht: (2024)

Accelerating Multi-Task Temporal Difference Learning under Low-Rank Representation
von: Bai, Yitao, et al.
Veröffentlicht: (2025)

Learning in Herding Mean Field Games: Single-Loop Algorithm with Finite-Time Convergence Analysis
von: Zeng, Sihan, et al.
Veröffentlicht: (2024)

Satisficing Paths and Independent Multi-Agent Reinforcement Learning in Stochastic Games
von: Yongacoglu, Bora, et al.
Veröffentlicht: (2021)

Energy-Optimal Multi-Agent Navigation as a Strategic-Form Game
von: Beaver, Logan
Veröffentlicht: (2024)

Convergence of Multi-Scale Reinforcement Q-Learning Algorithms for Mean Field Game and Control Problems
von: Angiuli, Andrea, et al.
Veröffentlicht: (2023)

Partially Observed Optimal Stochastic Control: Regularity, Optimality, Approximations, and Learning
von: Kara, Ali Devran, et al.
Veröffentlicht: (2024)

Finite Approximations for Mean Field Type Multi-Agent Control and Their Near Optimality
von: Bayraktar, Erhan, et al.
Veröffentlicht: (2022)

On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization
von: Tyurin, Alexander, et al.
Veröffentlicht: (2024)

Multi-Agent Relative Investment Games in a Jump Diffusion Market with Deep Reinforcement Learning Algorithm
von: Lu, Liwei, et al.
Veröffentlicht: (2024)

Distributed Optimal Control and Application to Consensus of Multi-Agent Systems
von: Zhang, Liping, et al.
Veröffentlicht: (2023)

A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning
von: Zeng, Sihan, et al.
Veröffentlicht: (2026)

Homogenization and Mean-Field Approximation for Multi-Player Games
von: Cont, Rama, et al.
Veröffentlicht: (2025)

On Passivity, Reinforcement Learning and Higher-Order Learning in Multi-Agent Finite Games
von: Gao, Bolin, et al.
Veröffentlicht: (2018)

DASA: Delay-Adaptive Multi-Agent Stochastic Approximation
von: Fabbro, Nicolò Dal, et al.
Veröffentlicht: (2024)

Efficient Online Mirror Descent Stochastic Approximation for Multi-Stage Stochastic Programming
von: Zhang, Junhui, et al.
Veröffentlicht: (2025)

Distributed Stochastic Block Coordinate Descent for Time-Varying Multi-Agent Optimization
von: Yu, Zhan, et al.
Veröffentlicht: (2019)

Time-Varying Distributed Optimization for A Class of Stochastic Multi-Agent Systems
von: Li, Wan-ying, et al.
Veröffentlicht: (2025)

Approximating the Uniform Value in Hidden Stochastic Games with Doeblin Conditions
von: Chatterjee, Krishnendu, et al.
Veröffentlicht: (2026)

State Constrained Optimal Control Problems With Control On The Acceleration. Applications To Kinetic Mean Field Games
von: Achdou, Yves
Veröffentlicht: (2025)

Finite-Time Analysis of Projected Two-Time-Scale Stochastic Approximation
von: Bai, Yitao, et al.
Veröffentlicht: (2026)

Stochastic Graphon Games with Jumps and Approximate Nash Equilibria
von: Amini, Hamed, et al.
Veröffentlicht: (2023)

Exploiting Approximate Symmetry for Efficient Multi-Agent Reinforcement Learning
von: Yardim, Batuhan, et al.
Veröffentlicht: (2024)

Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation
von: Han, Yuze, et al.
Veröffentlicht: (2024)

Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning
von: Zhang, Runyu, et al.
Veröffentlicht: (2025)

Stochastic Multi-objective Multi-trip AMR Routing Problem with Time Windows
von: Cheng, Lulu, et al.
Veröffentlicht: (2024)

QCQP-Net: Reliably Learning Feasible Alternating Current Optimal Power Flow Solutions Under Constraints
von: Zeng, Sihan, et al.
Veröffentlicht: (2024)

Optimal Control of Multi-Agent Systems with Processing Delays
von: Kashyap, Mruganka, et al.
Veröffentlicht: (2022)

Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games with Local Control and Global State Information
von: Yongacoglu, Bora, et al.
Veröffentlicht: (2019)

Reinforcement Learning Framework For Stochastic Optimal Control Problem Under Model Uncertainty
von: Hou, Jiaxuan, et al.
Veröffentlicht: (2025)

Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noise
von: Haque, Shaan Ul, et al.
Veröffentlicht: (2023)

Density-Driven Optimal Control: Convergence Guarantees for Stochastic LTI Multi-Agent Systems
von: Lee, Kooktae
Veröffentlicht: (2026)

Distributed Stochastic Search for Multi-Agent Model Predictive Control
von: Yoon, Taehyun, et al.
Veröffentlicht: (2025)

Distributed Optimal Consensus of Nonlinear Multi-Agent Systems
von: Guo, Ziyuan, et al.
Veröffentlicht: (2026)

Optimal Doubling Thresholds in Backgammon-like Stochastic Games
von: Ju, Haoru, et al.
Veröffentlicht: (2024)