Research map / Bandits and online learning / Online convex optimization and games
Online Learning in Stabilized Linear Dynamical Games with Adversarial Disturbances
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies online learning in stabilized linear dynamical games with adversarial disturbances, extending nonstochastic online control and linear-quadratic games.
Problem
Online learning for multiple strategic agents acting on a shared linear dynamical system subject to adversarial disturbances, beyond single-agent nonstochastic online control and classical LQ games with quadratic objectives and stochastic/noiseless dynamics.
Approach
Extends online control to multi-agent linear dynamical games under adversarial disturbances, moving beyond quadratic objectives and noiseless or stochastic dynamics; the abstract does not specify the algorithm.
Experimental setup
Builds on: nonstochastic online control linear-quadratic games
Closest papers by meaning
- Online Nonstochastic Model-Free Reinforcement Learning (NeurIPS 2023 · similarity 0.91)
- Online Control with Adversarial Disturbance for Continuous-time Linear Systems (NeurIPS 2024 · similarity 0.90)
- Robust and Diverse Multi-Agent Learning via Rational Policy Gradient (NeurIPS 2025 · similarity 0.88)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.87)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.87)
- Foundations of Multi-Agent Learning in Dynamic Environments: Where Reinforcement Learning Meets Strategic Decision-Making (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.