Decentralized Optimal Equilibrium Learning In Stochastic Games Via Single-bit Feedback

Abstract

We study decentralized equilibrium selection in stochastic games under severe information and communication constraints. In such settings, convergence to equilibrium alone is insufficient, as stochastic games typically admit many equilibria with markedly different welfare properties. We address decentralized optimal equilibrium selection, where agents coordinate on equilibria that optimize a designer-specified social welfare objective while allowing heterogeneous tolerance to deviations from strict best responses. Agents observe only the global state trajectory and their realized rewards, and exchange a single randomized bit of feedback per agent per round. This semantic content/discontent signaling mechanism implicitly aligns decentralized learning dynamics with the global welfare objective. We develop explore-and-commit and online variants applicable to general stochastic games, accommodating heterogeneous model-based or model-free methods for solving the induced Markov decision proc

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykiremitci2026decentralized

Related papers

• Achieving Pareto Optimality In Games Via Single-bit Feedback (2025)0.00
• Actor-dual-critic Dynamics For Zero-sum And Identical-interest Stochastic Games (2026)0.00
• Impact Of Decentralized Learning On Player Utilities In Stackelberg Games (2024)0.00
• Provably Efficient Reinforcement Learning In Decentralized General-sum Markov Games (2021)0.00
• Decentralized Reinforcement Learning: Global Decision-making Via Local Economic Transactions (2020)0.00
• Equilibrium Selection For Multi-agent Reinforcement Learning: A Unified Framework (2024)0.00
• Regret Minimization And Convergence To Equilibria In General-sum Markov Games (2022)0.00
• Independent And Decentralized Learning In Markov Potential Games (2022)0.00