AIBPO: Combine the Intrinsic Reward and Auxiliary Task for 3D Strategy Game.
Huale LiRui CaoXuan WangXiaohan HouTao QianFengwei JiaJiajia ZhangShuhan QiPublished in: Complex. (2021)
Keyphrases
- optimal strategy
- computer games
- game ai
- imperfect information
- selection strategy
- video games
- virtual world
- stackelberg game
- monte carlo
- game theory
- nash equilibrium
- game playing
- reinforcement learning
- two player games
- cooperative game
- decision making
- evolutionary game
- geometric structure
- game play
- resource allocation
- supply chain
- dynamic programming