Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors.
Kolby NottinghamYasaman RazeghiKyungmin KimJB LanierPierre BaldiRoy FoxSameer SinghPublished in: CoRR (2023)
Keyphrases
- language model
- reinforcement learning
- language modeling
- selective perception
- n gram
- state space
- document retrieval
- speech recognition
- retrieval model
- information retrieval
- query expansion
- ad hoc information retrieval
- language modelling
- mixture model
- statistical language models
- context sensitive
- probabilistic model
- markov decision processes
- test collection
- query terms
- multi agent
- relevance model
- smoothing methods
- learning process
- document length
- function approximation
- pseudo relevance feedback
- markov chain