Robust Reinforcement Learning for General Video Game Playing.
Chengpeng HuZiqi WangTianye ShuYang TaoHao TongJulian TogeliusXin YaoJialin LiuPublished in: CoRR (2020)
Keyphrases
- game playing
- reinforcement learning
- temporal difference learning
- video data
- general game playing
- multi agent
- imperfect information
- video sequences
- optimal policy
- video games
- adventure game
- multi player
- board game
- active exploration
- learning algorithm
- game tree search
- function approximation
- video frames
- markov chain
- social media
- e learning