Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning.
Juan RocamondeVictoriano MontesinosElvis NavaEthan PerezDavid LindnerPublished in: CoRR (2023)
Keyphrases
- language model
- reinforcement learning
- probabilistic model
- language modelling
- statistical language models
- language modeling
- smoothing methods
- speech recognition
- n gram
- relevance model
- document retrieval
- retrieval model
- term dependencies
- context sensitive
- information retrieval
- statistical models
- test collection
- query terms
- ir models
- information retrieval systems
- keywords
- language models for information retrieval
- language model for information retrieval