.png){kind=icon}
.png){kind=icon}
Return
Explore Reinforced: Equilibrium Approximation with Reinforcement Learning
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-08064-6_3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Current approximate Coarse Correlated Equilibria (CCE) algorithms struggle with equilibrium approximation for games in large stochastic environments. While these game-theoretic methods are theoretically guaranteed to converge to a strong solution concept, reinforcement learning (RL) algorithms have shown increasing capability in such environments but lack the equilibrium guarantees provided by game-theoretic approaches. In this paper, we introduce Exp3-IXRL - an equilibrium approximator that utilizes RL, specifically leveraging the agents action selection, to update equilibrium approximations while preserving the integrity of both learning processes. We therefore extend the Exp3 algorithms beyond the stateless, non-stochastic settings. Empirically, we demonstrate improved performance in classic non-stochastic multi-armed bandit settings, capability in stochastic multi-armed bandits, and strong results in a complex and adversarial cybersecurity network environment.
Keywords:
Reinforcement Learning
Game Theory
Coarse Correlated Equilibrium
Nash Equilibrium
Machine Learning
Journal
G
IF:
0
Papers:
16
Citations:
0