Decentralized learning in two-player zero-sum games: A LR-I lagging anchor algorithm.
Xiaosong LuHoward M. SchwartzPublished in: ACC (2011)
Keyphrases
- learning algorithm
- detection algorithm
- learning phase
- learning speed
- objective function
- computational cost
- dynamic programming
- cost function
- incremental learning
- learning process
- reinforcement learning
- k means
- machine learning
- search space
- preprocessing
- optimal solution
- similarity measure
- evolutionary algorithm
- np hard
- online learning
- particle swarm optimization
- expectation maximization
- learning agents