DanZero+: Dominating the GuanDan Game through Reinforcement Learning.
Youpeng ZhaoYudong LuJian ZhaoWengang ZhouHouqiang LiPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- video games
- game theory
- game playing
- game theoretic
- computer games
- markov decision processes
- optimal policy
- temporal difference
- state space
- temporal difference learning
- perfect information
- nash equilibrium
- game design
- reinforcement learning algorithms
- cooperative
- model free
- robotic control
- two player games
- stochastic games
- learning algorithm
- educational games
- virtual world
- transfer learning
- learning classifier systems
- game development
- imperfect information
- game play
- learning agents
- human computation
- monte carlo tree search
- learning problems
- role playing
- agent learns