Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games.

Gabriele Farina Robin Schmucker Tuomas Sandholm

Published in: AAAI (2021)

Keyphrases

sequential decision making
influence diagrams
extensive form games
decision problems
reinforcement learning
interactive dynamic influence diagrams
probabilistic inference
optimization algorithm
data mining
optimization problems
graphical models
sensitivity analysis
neural network
dynamic programming