Offline pre-trained multi-agent decision transformer

HIGHLIGHTS

  • who: April and collaborators from the Institute of Automation, Chinese Academy of Sciences, Beijing, China of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China have published the research: Offline Pre-trained Multi-agent Decision Transformer, in the Journal: (JOURNAL)
  • what: The authors investigate the generalization of MARL pre-training in the following three aspects: 1) between single agents and multiple agents 2) from pretraining to online fine tuning and 3) to that of multiple downstream tasks with few-shot and zero-shot capabilities. The authors propose multi-agent decision transformers (MADT), an architecture . . .

     

    Logo ScioWire Beta black

    If you want to have access to all the content you need to log in!

    Thanks :)

    If you don't have an account, you can create one here.

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?