
Generalization in portfoliobased algorithm selection
Portfoliobased algorithm selection has seen tremendous practical succes...
read it

Improving PolicyConstrained Kidney Exchange via PreScreening
In barter exchanges, participants swap goods with one another without ex...
read it

Faster Algorithms for Optimal ExAnte Coordinated Collusive Strategies in ExtensiveForm ZeroSum Games
We focus on the problem of finding an optimal strategy for a team of two...
read it

Finding and Certifying (Near)Optimal Strategies in BlackBox ExtensiveForm Games
Often – for example in war games, strategy video games, and financial si...
read it

PolynomialTime Computation of Optimal Correlated Equilibria in TwoPlayer ExtensiveForm Games with Public Chance Moves and Beyond
Unlike normalform games, where correlated equilibria have been studied ...
read it

Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent
Blackwell approachability is a framework for reasoning about repeated ga...
read it

Small Nash Equilibrium Certificates in Very Large Games
In many game settings, the game is not explicitly given but is only acce...
read it

Refined bounds for algorithm configuration: The knifeedge of dual class approximability
Automating algorithm configuration is growing increasingly necessary as ...
read it

Sparsified Linear Programming for ZeroSum Equilibrium Finding
Computational equilibrium finding in large zerosum extensiveform imper...
read it

Efficient exploration of zerosum stochastic games
We investigate the increasingly important and common gamesolving settin...
read it

Stochastic Regret Minimization in ExtensiveForm Games
MonteCarlo counterfactual regret minimization (MCCFR) is the stateoft...
read it

Efficient Regret Minimization Algorithm for ExtensiveForm Correlated Equilibrium
Selfplay methods based on regret minimization have become the state of ...
read it

Optimistic Regret Minimization for ExtensiveForm Games via Dilated DistanceGenerating Functions
We study the performance of optimistic regretminimization algorithms fo...
read it

Coarse Correlation in ExtensiveForm Games
Coarse correlation models strategic interactions of rational agents comp...
read it

How much data is sufficient to learn highperforming algorithms?
Algorithms for scientific analysis typically have tunable parameters tha...
read it

Correlation in ExtensiveForm Games: SaddlePoint Formulation and Benchmarks
While Nash equilibrium in extensiveform games is well understood, very ...
read it

Learning to Optimize Computational Resources: Frugal Training with Generalization Guarantees
Algorithms typically come with tunable parameters that have a considerab...
read it

Estimating Approximate Incentive Compatibility
In practice, most mechanisms for selling, buying, matching, voting, and ...
read it

Limited Lookahead in ImperfectInformation Games
Limited lookahead has been studied for decades in completeinformation g...
read it

StablePredictive Optimistic Counterfactual Regret Minimization
The CFR framework has been a powerful tool for solving largescale exten...
read it

QuasiPerfect Stackelberg Equilibrium
Equilibrium refinements are important in extensiveform (i.e., treeform...
read it

Regret Circuits: Composability of Regret Minimizers
Regret minimization is a powerful tool for solving largescale problems;...
read it

Composability of Regret Minimizers
Regret minimization is a powerful tool for solving largescale problems;...
read it

Deep Counterfactual Regret Minimization
Counterfactual Regret Minimization (CFR) is the leading algorithm for so...
read it

Solving Large Sequential Games with the Excessive Gap Technique
There has been tremendous recent progress on equilibriumfinding algorit...
read it

Solving ImperfectInformation Games via Discounted Regret Minimization
Counterfactual regret minimization (CFR) is a family of iterative algori...
read it

Online Convex Optimization for Sequential Decision Processes and ExtensiveForm Games
Regret minimization is a powerful tool for solving largescale extensive...
read it

DepthLimited Solving for ImperfectInformation Games
A fundamental challenge in imperfectinformation games is that states do...
read it

Learning to Branch
Tree search algorithms, such as branchandbound, are the most widely us...
read it

Robust Stackelberg Equilibria in ExtensiveForm Games and Extension to Limited Lookahead
Stackelberg equilibria have become increasingly important as a solution ...
read it

On the Verification and Computation of Strong Nash Equilibrium
Computing equilibria of games is a central task in computer science. A l...
read it

Regret Minimization in BehaviorallyConstrained ZeroSum Games
Noregret learning has emerged as a powerful tool for solving extensive...
read it

Operation Frames and Clubs in Kidney Exchange
A kidney exchange is a centrallyadministered barter market where patien...
read it

Safe and Nested Subgame Solving for ImperfectInformation Games
In imperfectinformation games, the optimal strategy in a subgame may de...
read it

Theoretical and Practical Advances on Smoothing for ExtensiveForm Games
Sparse iterative methods, in particular firstorder methods, are known t...
read it

Reduced Space and Faster Convergence in ImperfectInformation Games via RegretBased Pruning
Counterfactual Regret Minimization (CFR) is the most popular iterative a...
read it

PositionIndexed Formulations for Kidney Exchange
A kidney exchange is an organized barter market where patients in need o...
read it

Algorithms for Closed Under Rational Behavior (CURB) Sets
We provide a series of algorithms demonstrating that solutions according...
read it

Common Voting Rules as Maximum Likelihood Estimators
Voting is a very general method of preference aggregation. A voting rule...
read it

Universal Voting Protocol Tweaks to Make Manipulation Hard
Voting is a general method for preference aggregation in multiagent sett...
read it

Complexity of Determining Nonemptiness of the Core
Coalition formation is a key problem in automated negotiation among self...
read it

BLWoLF: A Framework For LossBounded Learnability In ZeroSum Games
We present BLWoLF, a framework for learnability in repeated zerosum ga...
read it

How many candidates are needed to make elections hard to manipulate?
In multiagent settings where the agents have different preferences, pref...
read it

AWESOME: A General Multiagent Learning Algorithm that Converges in SelfPlay and Learns a Best Response Against Stationary Opponents
A satisfactory multiagent learning algorithm should, at a minimum, lear...
read it

Vote Elicitation: Complexity and StrategyProofness
Preference elicitation is a central problem in AI, and has received sign...
read it

Complexity of Mechanism Design
The aggregation of conflicting preferences is a central problem in multi...
read it

Complexity Results about Nash Equilibria
Noncooperative game theory provides a normative framework for analyzing ...
read it

Anytime Coalition Structure Generation with Worst Case Guarantees
Coalition formation is a key topic in multiagent systems. One would pref...
read it
Tuomas Sandholm
is this you? claim profile
Director at Electronic Marketplaces Laboratory and Professor Carnegie Mellon University.