Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games.
The Viet BuiTien MaiThanh Hong NguyenPublished in: AAMAS (2023)
Keyphrases
- imperfect information
- imitation learning
- perfect information
- game theoretic
- nash equilibria
- game playing
- nash equilibrium
- reinforcement learning
- robotic systems
- maximum margin
- humanoid robot
- game theory
- human players
- game tree
- repeated games
- optimal policy
- stochastic games
- multi agent
- incomplete information
- action selection
- reinforcement learning algorithms
- xml documents
- relational databases
- reward function
- data points
- feature selection
- computer games
- relational domains
- transfer learning