Cuilt: A Scalable, Mix-and-Match Framework for Local Iterative Approximate Best-Response Algorithms.
Mihaela VermanPhilip StutzRobin HafenAbraham BernsteinPublished in: ECAI (2016)
Keyphrases
- main contribution
- lightweight
- recently developed
- data sets
- theoretical analysis
- data structure
- highly scalable
- optimization problems
- neural network
- real time
- computational efficiency
- memory efficient
- reinforcement learning
- approximate solutions
- highly efficient
- graph theory
- combinatorial optimization
- times faster
- benchmark datasets
- machine learning
- learning algorithm
- worst case
- probabilistic model
- significant improvement