Partial Information as Full: Reward Imputation with Sketching in Bandits.
Xiao ZhangNinglu ShaoZihua SiJun XuWenhan WangHanjing SuJi-Rong WenPublished in: CoRR (2022)
Keyphrases
- partial information
- multi armed bandit
- missing values
- incomplete information
- multi armed bandits
- bandit problems
- missing data
- reinforcement learning
- stochastic systems
- sketch recognition
- long run
- multi agent
- missing data imputation
- data imputation
- planning domains
- autonomous agents
- artificial intelligence
- multi armed bandit problems