Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts.
Jing-Cheng PangSi-Hang YangKaiyuan LiJiaji ZhangXiong-Hui ChenNan TangYang YuPublished in: CoRR (2024)
Keyphrases
- language model
- reinforcement learning
- multi agent
- language modeling
- document retrieval
- probabilistic model
- action selection
- n gram
- language modelling
- speech recognition
- learning agent
- information retrieval
- retrieval model
- query expansion
- state space
- test collection
- mixture model
- pseudo relevance feedback
- reinforcement learning algorithms
- multiagent reinforcement learning
- smoothing methods
- context sensitive
- vector space model
- markov decision processes
- query specific
- query terms
- machine learning
- statistical language models
- ad hoc information retrieval
- relevance model
- translation model
- temporal difference
- model free
- optimal policy
- pseudo feedback
- language model for information retrieval