FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning.
Yuwei FuHaichao ZhangDi WuWei XuBenoit BouletPublished in: CoRR (2024)
Keyphrases
- language model
- reinforcement learning
- language modeling
- probabilistic model
- n gram
- retrieval model
- markov decision processes
- information retrieval
- language modelling
- document retrieval
- speech recognition
- query expansion
- test collection
- visual information
- state space
- statistical language models
- optimal policy
- document ranking
- learning algorithm
- relevance model
- context sensitive
- visual features
- reward function
- vector space model
- term dependencies
- smoothing methods
- machine learning
- okapi bm
- language models for information retrieval
- spoken term detection
- language model for information retrieval
- query terms
- active learning
- document length
- low level