Learning payoff functions in infinite games
The authors 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. They 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, they consider the relative utility of prescribed strategy, rather than the accuracy of payoff functions per se. They check their approach 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, they explore the efficacy of using relative utility of strategies as a target of supervised learning and as a learning model selector. Their experiments demonstrate effectiveness in the former case, though not in the latter.
- Learning in games with continuous action sets and unknown payoff functions
- Learning in games with risky payoffs
- Learning equilibria of games via payoff queries
- On gradient-based learning in continuous games
- Learning efficient equilibria in repeated games
- Learning in games via reinforcement and regularization
- Learning with minimal information in continuous games
- Learning in Mean-Field Games
- scientific article; zbMATH DE number 7042419
- Generalized reinforcement learning in perfect-information games
- Efficient learning equilibrium
- Evolutionary Games in Economics
- scientific article; zbMATH DE number 1233801 (Why is no real title available?)
- scientific article; zbMATH DE number 2000817 (Why is no real title available?)
- scientific article; zbMATH DE number 823069 (Why is no real title available?)
- If multi-agent learning is the answer, what is the question?
- Microeconomic theory
- Non-cooperative games
- Remarks on Nash equilibria for games with additively coupled payoffs
- The elements of statistical learning. Data mining, inference, and prediction
- A unifying learning framework for building artificial game-playing agents
- Independent Log-Linear Learning in Potential Games With Continuous Actions
- scientific article; zbMATH DE number 7042419 (Why is no real title available?)
- Evaluating strategic structures in multi-agent inverse reinforcement learning
- Exploiting extensive-form structure in empirical game-theoretic analysis
- Data-driven entropic spatially inhomogeneous evolutionary games
- Empirical game theoretic analysis: a survey
- Stackelberg contention games in multiuser networks
This page was built for publication: Learning payoff functions in infinite games
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2384147)
