Knowru: knowledge reuse via knowledge distillation in multi-agent reinforcement learning

HIGHLIGHTS

• who: Zijian Gao and colleagues from the College of Computer, National University of Defense Technology, Changsha, China have published the research: KnowRU: Knowledge Reuse via Knowledge Distillation in Multi-Agent Reinforcement Learning, in the Journal: Entropy 2021, 23, 1043. of /2021/
• what: The authors propose a method for reuse called "KnowRU" which can be easily deployed in the majority of multi-agent reinforcement learning (MARL) algorithms without requiring complicated hand-coded design. The authors propose a task-independent KD framework for MARL, which focuses on not only accelerating the training phase, but also improving asymptotic . . .
  

   

  

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

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

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