Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models.
Fuxiang ZhangJunyou LiYi-Chen LiZongzhang ZhangYang YuDeheng YePublished in: CoRR (2024)
Keyphrases
- background knowledge
- language model
- reinforcement learning
- language modeling
- inductive logic programming
- domain knowledge
- logic programs
- probabilistic model
- n gram
- query expansion
- statistical language models
- language modelling
- retrieval model
- information retrieval
- document retrieval
- prior knowledge
- document representation
- test collection
- vector space model
- smoothing methods
- training data
- language models for information retrieval
- pseudo relevance feedback
- relevance model
- semantic relatedness
- document ranking
- semantic information
- transfer learning
- text categorization
- labeled data
- context aware
- low level
- learning process
- decision trees
- knowledge base
- learning algorithm