Prediction-aware Learning In Multi-agent Systems

Abstract

The framework of uncoupled online learning in multiplayer games has made significant progress in recent years. In particular, the development of time-varying games has considerably expanded its modeling capabilities. However, current regret bounds quickly become vacuous when the game undergoes significant variations over time, even when these variations are easy to predict. Intuitively, the ability of players to forecast future payoffs should lead to tighter guarantees, yet existing approaches fail to incorporate this aspect. This work aims to fill this gap by introducing a novel prediction-aware framework for time-varying games, where agents can forecast future payoffs and adapt their strategies accordingly. In this framework, payoffs depend on an underlying state of nature that agents predict in an online manner. To leverage these predictions, we propose the POWMU algorithm, a contextual extension of the optimistic Multiplicative Weight Update algorithm, for which we establish theore

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycapitaine2025prediction

Related papers

• No-regret Learning In Unknown Games With Correlated Payoffs (2019)0.00
• Multi-agent Online Learning In Time-varying Games (2018)8.82
• Distributed No-regret Learning In Multi-agent Systems (2020)0.00
• Sample-efficient Distributionally Robust Multi-agent Reinforcement Learning Via Online Interaction (2025)0.00
• Incentivize Without Bonus: Provably Efficient Model-based Online Multi-agent RL For Markov Games (2025)0.00
• Online Off-policy Prediction (2018)0.00
• Embedded Universal Predictive Intelligence: A Coherent Framework For Multi-agent Learning (2025)0.00
• Non-cooperative Multi-agent Systems With Exploring Agents (2020)0.00