Automatic Difficulty Balance in Two-Player Games with Deep Reinforcement Learning.
Simão ReisRita NovaisLuís Paulo ReisNuno LauPublished in: CoG (2023)
Keyphrases
- reinforcement learning
- two player games
- temporal difference learning
- evaluation function
- function approximation
- reinforcement learning algorithms
- supervised learning
- multi agent
- optimal policy
- machine learning
- learning process
- dynamic programming
- dynamic environments
- action selection
- temporal difference
- reinforcement learning methods