Multiplayer Stackelberg-Nash Game for Nonlinear System via Value Iteration-Based Integral Reinforcement Learning.
Man LiJiahu QinNikolaos M. FrerisDaniel W. C. HoPublished in: IEEE Trans. Neural Networks Learn. Syst. (2022)
Keyphrases
- nash equilibrium
- reinforcement learning
- game theory
- nash equilibria
- markov decision processes
- state space
- imperfect information
- game theoretic
- optimal policy
- stackelberg game
- markov decision process
- policy iteration
- computer games
- stochastic games
- online game
- mixed strategy
- dynamic programming
- incomplete information
- educational games
- partially observable markov decision processes
- reinforcement learning algorithms
- game play
- function approximation
- equilibrium strategies
- serious games
- multiagent learning
- heuristic search
- mobile games
- model free
- worst case
- average reward
- finite state
- solution concepts
- cooperative
- learning algorithm
- multi agent reinforcement learning
- decision problems
- belief space
- learning process
- multi agent systems
- action selection
- game development
- video games
- cooperative game
- resource allocation
- machine learning
- multi player
- game design
- reward function
- temporal difference