DanZero: Mastering GuanDan Game with Reinforcement Learning.
Yudong LuJian ZhaoYoupeng ZhaoWengang ZhouHouqiang LiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- computer games
- game playing
- game theory
- function approximation
- video games
- markov decision processes
- machine learning
- model free
- game play
- educational games
- reinforcement learning agents
- temporal difference
- nash equilibrium
- learning algorithm
- learning process
- dynamic programming
- search algorithm
- coverage includes
- imperfect information
- digital games
- game design
- serious games
- state space
- transfer learning
- multi agent
- game based learning
- supervised learning
- nash equilibria
- virtual world
- learning agents
- optimal policy
- state abstraction
- role playing
- learning experience