Conference CONFRONTING REWARD MODEL OVEROPTIMIZATION WITH CONSTRAINED RLHF 2024 • 12th International Conference on Learning Representations Iclr 2024 Moskovitz T, Singh AK, Strouse DJ, Sandholm T, Salakhutdinov R, Dragan AD, McAleer S
Preprint Convergence of $\text{log}(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis 2024 Anagnostides I, Sandholm T
Conference Convergence of log(1/ϵ) for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis 2024 • Advances in Neural Information Processing Systems • 37: Anagnostides I, Sandholm T
Preprint Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games 2024 Zhang BH, Anagnostides I, Farina G, Sandholm T
Conference Efficient Size-based Hybrid Algorithm for Optimal Coalition Structure Generation 2024 • Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS • 2024-May:2492-2494 Taguelmimt R, Aknine S, Boukredera D, Changder N, Sandholm T
Conference Efficient Φ-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games 2024 • Advances in Neural Information Processing Systems • 37: Zhang BH, Anagnostides I, Farina G, Sandholm T
Preprint Exponential Lower Bounds on the Double Oracle Algorithm in Zero-Sum Games 2024 Zhang BH, Sandholm T
Conference Exponential Lower Bounds on the Double Oracle Algorithm in Zero-Sum Games 2024 • IJCAI International Joint Conference on Artificial Intelligence • 3032-3039 Zhang BH, Sandholm T
Conference Faster Optimal Coalition Structure Generation via Offline Coalition Selection and Graph-Based Search 2024 • IJCAI International Joint Conference on Artificial Intelligence • 238-248 Taguelmimt R, Aknine S, Boukredera D, Changder N, Sandholm T
Preprint Faster Optimal Coalition Structure Generation via Offline Coalition Selection and Graph-Based Search 2024 Taguelmimt R, Aknine S, Boukredera D, Changder N, Sandholm T
Conference GAME-THEORETIC ROBUST RL HANDLES TEMPORALLY-COUPLED PERTURBATIONS 2024 • 12th International Conference on Learning Representations Iclr 2024 Liang Y, Sun Y, Zheng R, Liu X, Eysenbach B, Sandholm T, Huang F, McAleer S
Conference Hidden-Role Games: Equilibrium Concepts and Computation 2024 106-107 Carminati L, Zhang BH, Farina G, Gatti N, Sandholm T
Journal Article How Much Data Is Sufficient to Learn High-Performing Algorithms? 2024 • Journal of the ACM • 71(5): Balcan M-F, Deblasio D, Dick T, Kingsford C, Sandholm T, Vitercik E
Preprint Imperfect-Recall Games: Equilibrium Concepts and Their Complexity 2024 Tewolde E, Zhang BH, Oesterheld C, Zampetakis M, Sandholm T, Goldberg PW, Conitzer V
Conference Imperfect-Recall Games: Equilibrium Concepts and Their Complexity 2024 • IJCAI International Joint Conference on Artificial Intelligence • 2994-3004 Tewolde E, Zhang BH, Oesterheld C, Zampetakis M, Sandholm T, Goldberg P, Conitzer V
Journal Article Learning to Branch: Generalization Guarantees and Limits of Data-Independent Discretization 2024 • Journal of the ACM • 71(2): Balcan M-F, Dick T, Sandholm T, Vitercik E
Conference MEDIATOR INTERPRETATION AND FASTER LEARNING ALGORITHMS FOR LINEAR CORRELATED EQUILIBRIA IN GENERAL EXTENSIVE-FORM GAMES 2024 • 12th International Conference on Learning Representations Iclr 2024 Zhang BH, Farina G, Sandholm T
Conference Model-Free Preference Elicitation 2024 • IJCAI International Joint Conference on Artificial Intelligence • 3493-3503 Martin C, Boutilier C, Meshi O, Sandholm T
Preprint New Sequence-Independent Lifting Techniques for Cutting Planes and When They Induce Facets 2024 Prasad S, Vitercik E, Balcan M-F, Sandholm T
Conference On the Complexity of Computing Sparse Equilibria and Lower Bounds for No-Regret Learning in Games 2024 • Leibniz International Proceedings in Informatics Anagnostides I, Kalavasis A, Sandholm T, Zampetakis M
Preprint On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria 2024 Zhang BH, Sandholm T
Conference On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria 2024 • Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence • 9969-9976 Zhang BH, Sandholm T
Journal Article Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property 2024 • Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence • 9451-9459 Anagnostides I, Panageas I, Farina G, Sandholm T
Preprint Scalable Mechanism Design for Multi-Agent Path Finding 2024 Friedrich P, Zhang Y, Curry M, Dierks L, McAleer S, Li J, Sandholm T, Seuken S
