Research map / Multi-agent systems and games / Games and equilibria
Countering Feedback Delays in Multi-Agent Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use synchronous, bounded feedback delays in OMD (Algorithm 1) instead of arbitrary delays | OMD in games under delays · continuous games with lambda-variational stable unique Nash equilibrium | convergence of last iterate to Nash equilibrium | Helped |
| Replace OMD with delayed mirror descent (DMD), which reuses the most recent available gradient set when no feedback arrives in a round | OMD under asynchronous, unbounded delays · continuous games with lambda-variational stable Nash equilibria | convergence of last iterate to Nash equilibrium | Helped |
| Allow asynchronous, out-of-order, and superlinearly growing delays (DMD with step size alpha_t = 1/(t log t log log t)) rather than bounded synchronous delays | DMD · theoretical delay assumption (Assumption 2) | satisfaction of delay assumption | No clear effect |
Closest papers by meaning
- Local and Adaptive Mirror Descents in Extensive-Form Games (NeurIPS 2024 · similarity 0.91)
- Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback (NeurIPS 2025 · similarity 0.88)
- Adaptively Perturbed Mirror Descent for Learning in Games (ICML 2024 · similarity 0.88)
- Learning from Delayed Feedback in Games via Extra Prediction (NeurIPS 2025 · similarity 0.87)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.87)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 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.