Improving Generalization with Active Learning
Machine Learning - Special issue on structured connectionist systems
The nature of statistical learning theory
The nature of statistical learning theory
Artificial Intelligence Review - Special issue on lazy learning
Making large-scale support vector machine learning practical
Advances in kernel methods
Computing best-response strategies in infinite games of incomplete information
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Efficient learning equilibrium
Artificial Intelligence
Exploring bidding strategies for market-based scheduling
Decision Support Systems - Special issue: The fourth ACM conference on electronic commerce
Generating trading agent strategies: analytic and empirical methods for infinite and large games
Generating trading agent strategies: analytic and empirical methods for infinite and large games
If multi-agent learning is the answer, what is the question?
Artificial Intelligence
Learning to Coordinate Efficiently: a model-based approach
Journal of Artificial Intelligence Research
Learning payoff functions in infinite games
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Learning graphical game models
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Stackelberg contention games in multiuser networks
EURASIP Journal on Advances in Signal Processing - Special issue on game theory in signal processing and communications
Strategic analysis with simulation-based games
Winter Simulation Conference
Learning equilibria of games via payoff queries
Proceedings of the fourteenth ACM conference on Electronic commerce
Hi-index | 0.00 |
We consider a class of games with real-valued strategies and payoff information available only in the form of data from a given sample of strategy profiles. Solving such games with respect to the underlying strategy space requires generalizing from the data to a complete payoff-function representation. We address payoff-function learning as a standard regression problem, with provision for capturing known structure (e.g., symmetry) in the multiagent environment. To measure learning performance, we consider the relative utility of prescribed strategies, rather than the accuracy of payoff functions per se. We demonstrate our approach and evaluate its effectiveness on two examples: a two-player version of the first-price sealed-bid auction (with known analytical form), and a five-player market-based scheduling game (with no known solution). Additionally, we explore the efficacy of using relative utility of strategies as a target of supervised learning and as a learning model selector. Our experiments demonstrate its effectiveness in the former case, though not in the latter.