Large Language Model is a Good Policy Teacher for Training Reinforcement Learning Agents.
Zihao ZhouBin HuPu ZhangChenyang ZhaoBin LiuPublished in: CoRR (2023)
Keyphrases
- language model
- reinforcement learning agents
- language modeling
- n gram
- probabilistic model
- document retrieval
- speech recognition
- retrieval model
- information retrieval
- mixture model
- language modelling
- query expansion
- dynamic environments
- context sensitive
- test collection
- ad hoc information retrieval
- optimal policy
- training set
- translation model
- smoothing methods
- reinforcement learning
- multi agent environments
- dirichlet prior