Two-player nonlinear Stackelberg differential game via off-policy integral reinforcement learning.
Xiaohong CuiJiayu ChenYang CuiSuan XuPublished in: J. Frankl. Inst. (2024)
Keyphrases
- nash equilibria
- nash equilibrium
- reinforcement learning
- game theory
- game theoretic
- reinforcement learning algorithms
- stochastic games
- stackelberg game
- perfect information
- incomplete information
- game playing
- repeated games
- imperfect information
- function approximation
- multi agent reinforcement learning
- worst case
- state space
- mixed strategy
- markov decision processes
- learning algorithm
- temporal difference learning
- learning agents
- temporal difference
- multi player
- decision problems
- multi agent systems
- cooperative
- multi agent
- multiagent reinforcement learning
- normal form games
- machine learning
- solution concepts
- learning process
- action space
- single agent
- optimal strategy
- computer games
- dynamic programming
- leader follower
- neural network