Score-based Equilibrium Learning In Multi-player Finite Games With Imperfect Information

Abstract

Real-world games, which concern imperfect information, multiple players, and simultaneous moves, are less frequently discussed in the existing literature of game theory. While reinforcement learning (RL) provides a general framework to extend the game theoretical algorithms, the assumptions that guarantee their convergence towards Nash equilibria may no longer hold in real-world games. Starting from the definition of the Nash distribution, we construct a continuous-time dynamic named imperfect-information exponential-decay score-based learning (IESL) to find approximate Nash equilibria in games with the above-mentioned features. Theoretical analysis demonstrates that IESL yields equilibrium-approaching policies in imperfect information simultaneous games with the basic assumption of concavity. Experimental results show that IESL manages to find approximate Nash equilibria in four canonical poker scenarios and significantly outperforms three other representative algorithms in 3-player L

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylu2023score

Related papers

• Model-free Learning For Two-player Zero-sum Partially Observable Markov Games With Perfect Recall (2021)0.00
• Deep Reinforcement Learning From Self-play In Imperfect-information Games (2016)0.00
• Combining Deep Reinforcement Learning And Search For Imperfect-information Games (2020)0.00
• Consistent Opponent Modeling In Imperfect-information Games (2025)0.00
• Sample-efficient Learning Of Correlated Equilibria In Extensive-form Games (2022)0.00
• Learning Equilibria From Data: Provably Efficient Multi-agent Imitation Learning (2025)0.00
• Explore Reinforced: Equilibrium Approximation With Reinforcement Learning (2024)0.00
• Model-based Reinforcement Learning For Offline Zero-sum Markov Games (2022)0.00