default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDTuomas Sandholm
Person information
- affiliation: Carnegie Mellon University, Pittsburgh, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j55]Maria-Florina Balcan
, Travis Dick, Tuomas Sandholm, Ellen Vitercik:
Learning to Branch: Generalization Guarantees and Limits of Data-Independent Discretization. J. ACM 71(2): 13:1-13:73 (2024)- [j54]Maria-Florina Balcan, Dan F. DeBlasio, Travis Dick, Carl Kingsford, Tuomas Sandholm, Ellen Vitercik:
How Much Data Is Sufficient to Learn High-Performing Algorithms? J. ACM 71(5): 32:1-32:58 (2024) - [c326]Ioannis Anagnostides, Ioannis Panageas, Gabriele Farina, Tuomas Sandholm:
Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property. AAAI 2024: 9451-9459 - [c325]Michael J. Curry, Vinzenz Thoma, Darshan Chakrabarti, Stephen McAleer, Christian Kroer, Tuomas Sandholm, Niao He, Sven Seuken:
Automated Design of Affine Maximizer Mechanisms in Dynamic Settings. AAAI 2024: 9626-9635 - [c324]Brian Hu Zhang, Tuomas Sandholm:
On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria. AAAI 2024: 9969-9976 - [c323]Redha Taguelmimt, Samir Aknine, Djamila Boukredera, Narayan Changder, Tuomas Sandholm:
A Multiagent Path Search Algorithm for Large-Scale Coalition Structure Generation. AAMAS 2024: 2489-2491 - [c322]Redha Taguelmimt, Samir Aknine, Djamila Boukredera, Narayan Changder, Tuomas Sandholm:
Efficient Size-based Hybrid Algorithm for Optimal Coalition Structure Generation. AAMAS 2024: 2492-2494 - [c321]Yongyuan Liang, Yanchao Sun, Ruijie Zheng, Xiangyu Liu, Benjamin Eysenbach, Tuomas Sandholm, Furong Huang, Stephen Marcus McAleer:
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations. ICLR 2024 - [c320]Stephen Marcus McAleer, JB Lanier, Kevin A. Wang, Pierre Baldi, Tuomas Sandholm, Roy Fox:
Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games. ICLR 2024 - [c319]Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen Marcus McAleer:
Confronting Reward Model Overoptimization with Constrained RLHF. ICLR 2024 - [c318]Brian Hu Zhang, Gabriele Farina, Tuomas Sandholm:
Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games. ICLR 2024 - [c317]Paul Friedrich, Yulun Zhang, Michael J. Curry, Ludwig Dierks, Stephen McAleer, Jiaoyang Li, Tuomas Sandholm, Sven Seuken:
Scalable Mechanism Design for Multi-Agent Path Finding. IJCAI 2024: 58-66 - [c316]Redha Taguelmimt, Samir Aknine, Djamila Boukredera, Narayan Changder, Tuomas Sandholm:
Faster Optimal Coalition Structure Generation via Offline Coalition Selection and Graph-Based Search. IJCAI 2024: 238-248 - [c315]Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld, Manolis Zampetakis, Tuomas Sandholm, Paul Goldberg, Vincent Conitzer:
Imperfect-Recall Games: Equilibrium Concepts and Their Complexity. IJCAI 2024: 2994-3004 - [c314]Brian Hu Zhang, Tuomas Sandholm:
Exponential Lower Bounds on the Double Oracle Algorithm in Zero-Sum Games. IJCAI 2024: 3032-3039 - [c313]Carlos Martin, Craig Boutilier, Ofer Meshi, Tuomas Sandholm:
Model-Free Preference Elicitation. IJCAI 2024: 3493-3503 - [c312]Ioannis Anagnostides, Alkis Kalavasis, Tuomas Sandholm, Manolis Zampetakis:
On the Complexity of Computing Sparse Equilibria and Lower Bounds for No-Regret Learning in Games. ITCS 2024: 5:1-5:24 - [c311]Brian Hu Zhang, Gabriele Farina, Ioannis Anagnostides, Federico Cacciamani, Stephen McAleer, Andreas A. Haupt, Andrea Celli, Nicola Gatti, Vincent Conitzer, Tuomas Sandholm:
Steering No-Regret Learners to a Desired Equilibrium. EC 2024: 73-74 - [c310]Luca Carminati, Brian Hu Zhang, Gabriele Farina, Nicola Gatti, Tuomas Sandholm:
Hidden-Role Games: Equilibrium Concepts and Computation. EC 2024: 106-107 - [i123]Siddharth Prasad, Ellen Vitercik, Maria-Florina Balcan, Tuomas Sandholm:
New Sequence-Independent Lifting Techniques for Cutting Planes and When They Induce Facets. CoRR abs/2401.13773 (2024) - [i122]Paul Friedrich, Yulun Zhang, Michael J. Curry, Ludwig Dierks, Stephen McAleer, Jiaoyang Li, Tuomas Sandholm, Sven Seuken:
Scalable Mechanism Design for Multi-Agent Path Finding. CoRR abs/2401.17044 (2024) - [i121]Brian Hu Zhang, Tuomas Sandholm:
On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria. CoRR abs/2402.05245 (2024) - [i120]Michael J. Curry, Vinzenz Thoma, Darshan Chakrabarti, Stephen McAleer, Christian Kroer, Tuomas Sandholm, Niao He, Sven Seuken:
Automated Design of Affine Maximizer Mechanisms in Dynamic Settings. CoRR abs/2402.08129 (2024) - [i119]Brian Hu Zhang, Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm:
Efficient Φ-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games. CoRR abs/2402.09670 (2024) - [i118]Naifeng Zhang, Stephen McAleer, Tuomas Sandholm:
Faster Game Solving via Hyperparameter Schedules. CoRR abs/2404.09097 (2024) - [i117]Brian Hu Zhang, Tuomas Sandholm:
Exponential Lower Bounds on the Double Oracle Algorithm in Zero-Sum Games. CoRR abs/2405.06797 (2024) - [i116]Carlos Martin, Tuomas Sandholm:
Simultaneous incremental support adjustment and metagame solving: An equilibrium-finding framework for continuous-action games. CoRR abs/2406.08683 (2024) - [i115]Carlos Martin, Tuomas Sandholm:
AlphaZeroES: Direct score maximization outperforms planning loss minimization. CoRR abs/2406.08687 (2024) - [i114]Constantinos Daskalakis, Gabriele Farina, Noah Golowich, Tuomas Sandholm, Brian Hu Zhang:
A Lower Bound on Swap Regret in Extensive-Form Games. CoRR abs/2406.13116 (2024) - [i113]Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld, Manolis Zampetakis, Tuomas Sandholm, Paul W. Goldberg, Vincent Conitzer:
Imperfect-Recall Games: Equilibrium Concepts and Their Complexity. CoRR abs/2406.15970 (2024) - [i112]Redha Taguelmimt, Samir Aknine, Djamila Boukredera, Narayan Changder, Tuomas Sandholm:
Faster Optimal Coalition Structure Generation via Offline Coalition Selection and Graph-Based Search. CoRR abs/2407.16092 (2024) - [i111]Carlos Martin, Tuomas Sandholm:
Joint-perturbation simultaneous pseudo-gradient. CoRR abs/2408.09306 (2024) - [i110]Fabian R. Pieroth, Tuomas Sandholm:
Verifying Approximate Equilibrium in Auctions. CoRR abs/2408.11445 (2024) - [i109]Ioannis Anagnostides, Tuomas Sandholm:
Convergence of log(1/ε) for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis. CoRR abs/2410.21636 (2024) - [i108]Ioannis Anagnostides, Alkis Kalavasis, Tuomas Sandholm:
Barriers to Welfare Maximization with No-Regret Learning. CoRR abs/2411.01720 (2024) - [i107]Ioannis Anagnostides, Alkis Kalavasis, Tuomas Sandholm:
Computational Lower Bounds for Regret Minimization in Normal-Form Games. CoRR abs/2411.01721 (2024) - 2023
- [c309]Keegan Harris, Ioannis Anagnostides, Gabriele Farina, Mikhail Khodak, Steven Wu, Tuomas Sandholm:
Meta-Learning in Games. ICLR 2023 - [c308]Stephen Marcus McAleer, Gabriele Farina, Marc Lanctot, Tuomas Sandholm:
ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret. ICLR 2023 - [c307]Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm:
Near-Optimal Φ-Regret Learning in Extensive-Form Games. ICML 2023: 814-839 - [c306]Brian Hu Zhang, Gabriele Farina, Tuomas Sandholm:
Team Belief DAG: Generalizing the Sequence Form to Team Games for Fast Computation of Correlated Team Max-Min Equilibria via Regret Minimization. ICML 2023: 40996-41018 - [c305]Redha Taguelmimt, Samir Aknine, Djamila Boukredera, Narayan Changder, Tuomas Sandholm:
Optimal Anytime Coalition Structure Generation Utilizing Compact Solution Space Representation. IJCAI 2023: 309-316 - [c304]Michael J. Curry, Tuomas Sandholm, John P. Dickerson:
Differentiable Economics for Randomized Affine Maximizer Auctions. IJCAI 2023: 2633-2641 - [c303]Carlos Martin, Tuomas Sandholm:
Finding Mixed-Strategy Equilibria of Continuous-Action Games without Gradients Using Randomized Policy Networks. IJCAI 2023: 2844-2852 - [c302]Ioannis Anagnostides, Ioannis Panageas, Gabriele Farina, Tuomas Sandholm:
On the Convergence of No-Regret Learning Dynamics in Time-Varying Games. NeurIPS 2023 - [c301]Ioannis Anagnostides, Tuomas Sandholm:
On the Interplay between Social Welfare and Tractability of Equilibria. NeurIPS 2023 - [c300]Stephen McAleer, Gabriele Farina, Gaoyue Zhou, Mingzhi Wang, Yaodong Yang, Tuomas Sandholm:
Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning. NeurIPS 2023 - [c299]Siddharth Prasad, Maria-Florina Balcan, Tuomas Sandholm:
Bicriteria Multidimensional Mechanism Design with Side Information. NeurIPS 2023 - [c298]Brian Hu Zhang, Gabriele Farina, Ioannis Anagnostides, Federico Cacciamani, Stephen McAleer, Andreas A. Haupt, Andrea Celli, Nicola Gatti, Vincent Conitzer, Tuomas Sandholm:
Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games. NeurIPS 2023 - [i106]Carlos Martin, Tuomas Sandholm:
Computing equilibria by minimizing exploitability with best-response ensembles. CoRR abs/2301.08830 (2023) - [i105]Ioannis Anagnostides, Ioannis Panageas, Gabriele Farina, Tuomas Sandholm:
On the Convergence of No-Regret Learning Dynamics in Time-Varying Games. CoRR abs/2301.11241 (2023) - [i104]Maria-Florina Balcan, Siddharth Prasad, Tuomas Sandholm:
Bicriteria Multidimensional Mechanism Design with Side Information. CoRR abs/2302.14234 (2023) - [i103]Brian Hu Zhang, Gabriele Farina, Ioannis Anagnostides, Federico Cacciamani, Stephen Marcus McAleer, Andreas Alexander Haupt, Andrea Celli, Nicola Gatti, Vincent Conitzer, Tuomas Sandholm:
Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games. CoRR abs/2306.05216 (2023) - [i102]Brian Hu Zhang, Gabriele Farina, Ioannis Anagnostides, Federico Cacciamani, Stephen Marcus McAleer, Andreas Alexander Haupt, Andrea Celli, Nicola Gatti, Vincent Conitzer, Tuomas Sandholm:
Steering No-Regret Learners to Optimal Equilibria. CoRR abs/2306.05221 (2023) - [i101]Yongyuan Liang, Yanchao Sun, Ruijie Zheng, Xiangyu Liu, Tuomas Sandholm, Furong Huang, Stephen McAleer:
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations. CoRR abs/2307.12062 (2023) - [i100]Carlos Martin, Tuomas Sandholm:
Planning in the imagination: High-level planning on learned abstract search spaces. CoRR abs/2308.08693 (2023) - [i99]Luca Carminati, Brian Hu Zhang, Gabriele Farina, Nicola Gatti, Tuomas Sandholm:
Hidden-Role Games: Equilibrium Concepts and Computation. CoRR abs/2308.16017 (2023) - [i98]Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen McAleer:
Confronting Reward Model Overoptimization with Constrained RLHF. CoRR abs/2310.04373 (2023) - [i97]Brian Hu Zhang, Gabriele Farina, Tuomas Sandholm:
Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Extensive-Form Games. CoRR abs/2310.15935 (2023) - [i96]Ioannis Anagnostides, Tuomas Sandholm:
On the Interplay between Social Welfare and Tractability of Equilibria. CoRR abs/2310.16976 (2023) - [i95]Ioannis Anagnostides, Alkis Kalavasis, Tuomas Sandholm, Manolis Zampetakis:
On the Complexity of Computing Sparse Equilibria and Lower Bounds for No-Regret Learning in Games. CoRR abs/2311.14869 (2023) - [i94]Ioannis Anagnostides, Ioannis Panageas, Gabriele Farina, Tuomas Sandholm:
Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property. CoRR abs/2312.12067 (2023) - 2022
- [c297]Gabriele Farina, Tuomas Sandholm:
Fast Payoff Matrix Sparsification Techniques for Structured Extensive-Form Games. AAAI 2022: 4999-5007 - [c296]Brian Hu Zhang, Tuomas Sandholm:
Team Correlated Equilibria in Zero-Sum Extensive-Form Games via Tree Decompositions. AAAI 2022: 5252-5259 - [c295]Maria-Florina Balcan, Siddharth Prasad, Tuomas Sandholm, Ellen Vitercik:
Improved Sample Complexity Bounds for Branch-And-Cut. CP 2022: 3:1-3:19 - [c294]Ioannis Anagnostides, Ioannis Panageas, Gabriele Farina, Tuomas Sandholm:
On Last-Iterate Convergence Beyond Zero-Sum Games. ICML 2022: 536-581 - [c293]Ioannis Anagnostides, Gabriele Farina, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Tuomas Sandholm:
Uncoupled Learning Dynamics with O(log T) Swap Regret in Multiplayer Games. NeurIPS 2022 - [c292]Ioannis Anagnostides, Gabriele Farina, Ioannis Panageas, Tuomas Sandholm:
Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games. NeurIPS 2022 - [c291]Maria-Florina Balcan, Siddharth Prasad, Tuomas Sandholm:
Maximizing Revenue under Market Shrinkage and Market Uncertainty. NeurIPS 2022 - [c290]Maria-Florina Balcan, Siddharth Prasad, Tuomas Sandholm, Ellen Vitercik:
Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts. NeurIPS 2022 - [c289]Gabriele Farina, Ioannis Anagnostides, Haipeng Luo, Chung-Wei Lee, Christian Kroer, Tuomas Sandholm:
Near-Optimal No-Regret Learning Dynamics for General Convex Games. NeurIPS 2022 - [c288]Brian Hu Zhang, Luca Carminati, Federico Cacciamani, Gabriele Farina, Pierriccardo Olivieri, Nicola Gatti, Tuomas Sandholm:
Subgame Solving in Adversarial Team Games. NeurIPS 2022 - [c287]Brian Hu Zhang, Tuomas Sandholm:
Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games. NeurIPS 2022 - [c286]Ioannis Anagnostides, Gabriele Farina, Christian Kroer, Andrea Celli, Tuomas Sandholm:
Faster No-Regret Learning Dynamics for Extensive-Form Correlated and Coarse Correlated Equilibria. EC 2022: 915-916 - [c285]Brian Hu Zhang, Gabriele Farina, Andrea Celli, Tuomas Sandholm:
Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation. EC 2022: 1119-1120 - [c284]Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina, Maxwell Fishelson, Noah Golowich, Tuomas Sandholm:
Near-optimal no-regret learning for correlated equilibria in multi-player general-sum games. STOC 2022: 736-749 - [i93]Stephen McAleer, Kevin Wang, John B. Lanier, Marc Lanctot, Pierre Baldi, Tuomas Sandholm, Roy Fox:
Anytime PSRO for Two-Player Zero-Sum Games. CoRR abs/2201.07700 (2022) - [i92]Brian Hu Zhang, Gabriele Farina, Tuomas Sandholm:
Team Belief DAG Form: A Concise Representation for Team-Correlated Game-Theoretic Decision Making. CoRR abs/2202.00789 (2022) - [i91]Michael J. Curry, Tuomas Sandholm, John P. Dickerson:
Differentiable Economics for Randomized Affine Maximizer Auctions. CoRR abs/2202.02872 (2022) - [i90]Ioannis Anagnostides, Gabriele Farina, Christian Kroer, Andrea Celli, Tuomas Sandholm:
Faster No-Regret Learning Dynamics for Extensive-Form Correlated and Coarse Correlated Equilibria. CoRR abs/2202.05446 (2022) - [i89]Brian Hu Zhang, Gabriele Farina, Andrea Celli, Tuomas Sandholm:
Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation. CoRR abs/2203.07181 (2022) - [i88]Ioannis Anagnostides, Ioannis Panageas, Gabriele Farina, Tuomas Sandholm:
On Last-Iterate Convergence Beyond Zero-Sum Games. CoRR abs/2203.12056 (2022) - [i87]Ioannis Anagnostides, Gabriele Farina, Ioannis Panageas, Tuomas Sandholm:
Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games. CoRR abs/2203.12074 (2022) - [i86]Maria-Florina Balcan, Siddharth Prasad, Tuomas Sandholm, Ellen Vitercik:
Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts. CoRR abs/2204.07312 (2022) - [i85]Ioannis Anagnostides, Gabriele Farina, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Tuomas Sandholm:
Uncoupled Learning Dynamics with O(log T) Swap Regret in Multiplayer Games. CoRR abs/2204.11417 (2022) - [i84]Stephen McAleer, Gabriele Farina, Marc Lanctot, Tuomas Sandholm:
ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret. CoRR abs/2206.04122 (2022) - [i83]Gabriele Farina, Ioannis Anagnostides, Haipeng Luo, Chung-Wei Lee, Christian Kroer, Tuomas Sandholm:
Near-Optimal No-Regret Learning for General Convex Games. CoRR abs/2206.08742 (2022) - [i82]Brian Hu Zhang, Tuomas Sandholm:
Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games. CoRR abs/2206.15395 (2022) - [i81]Stephen McAleer, John B. Lanier, Kevin A. Wang, Pierre Baldi, Roy Fox, Tuomas Sandholm:
Self-Play PSRO: Toward Optimal Populations in Two-Player Zero-Sum Games. CoRR abs/2207.06541 (2022) - [i80]Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm:
Near-Optimal $Φ$-Regret Learning in Extensive-Form Games. CoRR abs/2208.09747 (2022) - [i79]Keegan Harris, Ioannis Anagnostides, Gabriele Farina, Mikhail Khodak, Zhiwei Steven Wu, Tuomas Sandholm:
Meta-Learning in Games. CoRR abs/2209.14110 (2022) - [i78]Carlos Martin, Tuomas Sandholm:
Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks. CoRR abs/2211.15936 (2022) - 2021
- [j53]Robin Schmucker, Gabriele Farina, James R. Faeder, Fabian Fröhlich, Ali Sinan Saglam, Tuomas Sandholm:
Combination treatment optimization using a pan-cancer pathway model. PLoS Comput. Biol. 17(12) (2021) - [c283]Gabriele Farina, Christian Kroer, Tuomas Sandholm:
Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent. AAAI 2021: 5363-5371 - [c282]Gabriele Farina, Robin Schmucker, Tuomas Sandholm:
Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games. AAAI 2021: 5372-5380 - [c281]Gabriele Farina, Tuomas Sandholm:
Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games. AAAI 2021: 5381-5390 - [c280]Brian Hu Zhang, Tuomas Sandholm:
Finding and Certifying (Near-)Optimal Strategies in Black-Box Extensive-Form Games. AAAI 2021: 5779-5788 - [c279]Maria-Florina Balcan, Tuomas Sandholm, Ellen Vitercik:
Generalization in Portfolio-Based Algorithm Selection. AAAI 2021: 12225-12232 - [c278]Gabriele Farina, Andrea Celli, Nicola Gatti, Tuomas Sandholm:
Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results. ICML 2021: 3164-3173 - [c277]Maria-Florina Balcan, Siddharth Prasad, Tuomas Sandholm:
Learning Within an Instance for Designing High-Revenue Combinatorial Auctions. IJCAI 2021: 31-37 - [c276]Maria-Florina Balcan, Siddharth Prasad, Tuomas Sandholm, Ellen Vitercik:
Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond. NeurIPS 2021: 4015-4027 - [c275]Gabriele Farina, Tuomas Sandholm:
Equilibrium Refinement for the Age of Machines: The One-Sided Quasi-Perfect Equilibrium. NeurIPS 2021: 8845-8856 - [c274]Brian Hu Zhang, Tuomas Sandholm:
Subgame solving without common knowledge. NeurIPS 2021: 23993-24004 - [c273]Gabriele Farina, Christian Kroer, Tuomas Sandholm:
Better Regularization for Sequential Decision Spaces: Fast Convergence Rates for Nash, Correlated, and Team Equilibria. EC 2021: 432 - [c272]Maria-Florina Balcan, Dan F. DeBlasio, Travis Dick, Carl Kingsford, Tuomas Sandholm, Ellen Vitercik:
How much data is sufficient to learn high-performing algorithms? generalization guarantees for data-driven algorithm design. STOC 2021: 919-932 - [i77]Gabriele Farina, Tuomas Sandholm:
Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games. CoRR abs/2103.04539 (2021) - [i76]Gabriele Farina, Robin Schmucker, Tuomas Sandholm:
Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games. CoRR abs/2103.04546 (2021) - [i75]Gabriele Farina, Christian Kroer, Tuomas Sandholm:
Better Regularization for Sequential Decision Spaces: Fast Convergence Rates for Nash, Correlated, and Team Equilibria. CoRR abs/2105.12954 (2021) - [i74]Maria-Florina Balcan, Siddharth Prasad, Tuomas Sandholm, Ellen Vitercik:
Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond. CoRR abs/2106.04033 (2021) - [i73]Brian Hu Zhang, Tuomas Sandholm:
Subgame solving without common knowledge. CoRR abs/2106.06068 (2021) - [i72]Brian Hu Zhang, Tuomas Sandholm:
Team Correlated Equilibria in Zero-Sum Extensive-Form Games via Tree Decompositions. CoRR abs/2109.05284 (2021) - [i71]Gabriele Farina, Andrea Celli, Tuomas Sandholm:
Efficient Decentralized Learning Dynamics for Extensive-Form Coarse Correlated Equilibrium: No Expensive Computation of Stationary Distributions Required. CoRR abs/2109.08138 (2021) - [i70]Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina, Maxwell Fishelson, Noah Golowich, Tuomas Sandholm:
Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games. CoRR abs/2111.06008 (2021) - [i69]Maria-Florina Balcan, Siddharth Prasad, Tuomas Sandholm, Ellen Vitercik:
Improved Learning Bounds for Branch-and-Cut. CoRR abs/2111.11207 (2021) - [i68]Gabriele Farina, Tuomas Sandholm:
Fast Payoff Matrix Sparsification Techniques for Structured Extensive-Form Games. CoRR abs/2112.03804 (2021) - 2020
- [j52]Christian Kroer, Tuomas Sandholm:
Limited lookahead in imperfect-information games. Artif. Intell. 283: 103218 (2020) - [j51]Eleonora Braggion, Nicola Gatti, Roberto Lucchetti, Tuomas Sandholm, Bernhard von Stengel:
Strong Nash equilibria and mixed strategies. Int. J. Game Theory 49(3): 699-710 (2020) - [j50]