Generating and Evolving Reward Functions for Highway Driving with Large Language Models.
Xu HanQiannan YangXianda ChenXiaowen ChuMeixin ZhuPublished in: CoRR (2024)
Keyphrases
- language model
- reward function
- language modeling
- speech recognition
- probabilistic model
- n gram
- retrieval model
- document retrieval
- markov decision processes
- state variables
- context sensitive
- test collection
- reinforcement learning
- language modelling
- state space
- inverse reinforcement learning
- information retrieval
- smoothing methods
- statistical language models
- query expansion
- document ranking
- traffic accidents
- multiple agents
- query terms
- vector space model
- optimal policy
- relevance model
- document representation
- generative model
- automatic speech recognition
- information retrieval systems
- okapi bm