Towards Playing Full MOBA Games with Deep Reinforcement Learning.
Deheng YeGuibin ChenWen ZhangSheng ChenBo YuanBo LiuJia ChenZhao LiuFuhao QiuHongsheng YuYinyuting YinBei ShiLiang WangTengfei ShiQiang FuWei YangLanxiao HuangWei LiuPublished in: NeurIPS (2020)
Keyphrases
- reinforcement learning
- game playing
- computer games
- games played
- temporal difference learning
- foreign language learners
- game players
- online game
- action sets
- imperfect information
- learning agents
- board game
- reinforcement learning agents
- function approximation
- video games
- multi player
- card games
- two player games
- state space
- game design
- reinforcement learning algorithms
- general game playing
- model free
- card game
- human players
- computer poker
- digital games
- nash equilibria
- multi agent
- supervised learning
- educational games
- game play
- game tree
- perfect information
- machine learning
- markov decision processes
- optimal policy
- learning algorithm
- game based learning
- game theoretic
- playing games
- human computation
- nash equilibrium
- robotic control
- coalitional games
- cooperative
- stochastic games