Tuomas Sandholm
~Tuomas_Sandholm1
9
论文总数
4.5
年均投稿
平均评分
接收情况8/9
会议分布
ICLR
5
NeurIPS
3
ICML
1
发表论文 (9 篇)
20252 篇
20247 篇
5
Convergence of $\text{log}(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis
NeurIPS 2024Poster
4
Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games
ICLR 2024Poster
3
Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games
NeurIPS 2024Poster
4
Confronting Reward Model Overoptimization with Constrained RLHF
ICLR 2024Spotlight
3
Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games
ICLR 2024Poster
3
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
ICLR 2024Poster
4
Steering No-Regret Learners to Optimal Equilibria
ICLR 2024Rejected