search

dunnolab / awesome-in-context-rl

Awesome In-Context RL: A curated list of In-Context Reinforcement Learning
96 stars 7 forks source link

Missing papers #6

Closed weiqinchen7 closed 3 weeks ago

weiqinchen7 commented 3 weeks ago

Hi, thank you for collecting the amazing ICRL literature. I believe there are some missing ICRL papers as shown below. Thanks!

Can large language models explore in-context?

SAD: State-Action Distillation for In-Context Reinforcement Learning under Random Policies

Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning

Transformers Learn Temporal Difference Methods for In-Context Reinforcement Learning

vkurenkov commented 3 weeks ago

Hi,

These all are very relevant papers, thanks for pointing out.

Could you create a pull request with these additions? We will merge ASAP.