nash equilibrium
A concept from game theory where no player can benefit from unilaterally changing their strategy given the strategies of all other players, often used in multi-agent reinforcement learning to establish stable action profiles.
- A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing
- Efficient Last-Iterate Convergence in Solving Extensive-Form Games
- LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory
- Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria
- Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning
- Learning from Delayed Feedback in Games via Extra Prediction
- On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
- Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form Games
- Principled Long-Tailed Generative Modeling via Diffusion Models
- Protocols for Verifying Smooth Strategies in Bandits and Games
- Scalable Neural Incentive Design with Parameterized Mean-Field Approximation
- Strategic Costs of Perceived Bias in Fair Selection
- Theoretical Guarantees for the Retention of Strict Nash Equilibria by Coevolutionary Algorithms