Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games.
The Viet BuiTien MaiThanh H. NguyenPublished in: CoRR (2022)
Keyphrases
- imperfect information
- imitation learning
- perfect information
- game theoretic
- nash equilibria
- nash equilibrium
- game playing
- game theory
- reinforcement learning
- robotic systems
- human players
- game tree
- humanoid robot
- maximum margin
- stochastic games
- optimal policy
- repeated games
- incomplete information
- multi agent
- decision problems
- learning algorithm