A novel heuristic Q-learning algorithm for solving stochastic games.
Jianwei LiWeiyi LiuPublished in: IJCNN (2008)
Keyphrases
- stochastic games
- learning algorithm
- reinforcement learning algorithms
- nash equilibria
- combinatorial optimization
- markov decision processes
- reinforcement learning
- optimal solution
- machine learning algorithms
- learning automata
- dynamic programming
- learning agent
- mathematical programming
- robust optimization
- machine learning
- average reward
- nash equilibrium
- search algorithm
- neural network
- solving problems
- transfer learning
- least squares
- repeated games