Development Tool of Q-Nash Learning Agent for Intelligent System.
Masato HibinoTakahiro UchiyaIchi TakumiTetsuo KinoshitaPublished in: NBiS (2015)
Keyphrases
- intelligent systems
- learning agent
- stochastic games
- reinforcement learning
- solving problems
- state space
- learning algorithm
- computational intelligence
- learning capabilities
- learning process
- nash equilibrium
- expert systems
- artificial intelligence
- learning tasks
- nash equilibria
- reinforcement learning algorithms
- soft computing
- single agent
- game theory
- selective perception
- utility function
- function approximation
- neural network
- model free
- transfer learning
- human level
- incomplete information
- evolutionary computation
- supervised learning
- pattern recognition
- search algorithm
- multi agent