Boosting Offline Reinforcement Learning with Action Preference Query.
Qisen YangShenzhi WangMatthieu Gaetan LinShiji SongGao HuangPublished in: ICML (2023)
Keyphrases
- reinforcement learning
- query processing
- database
- action selection
- response time
- function approximation
- query evaluation
- range queries
- real time
- database queries
- query expansion
- user queries
- partially observable domains
- user preferences
- data structure
- user interaction
- multi dimensional
- learning algorithm
- action space
- reward shaping
- machine learning
- test collection
- keywords
- feature selection
- query formulation
- temporal difference
- reinforcement learning algorithms