Attention-based fault-tolerant approach for multi-agent reinforcement learning systems

HIGHLIGHTS

• who: Shanzhi Gu and colleagues from the College of Computer, National University of Defense Technology, Changsha, China have published the research work: Attention-Based Fault-Tolerant Approach for Multi-Agent Reinforcement Learning Systems, in the Journal: Entropy 2021, 23, 1133. of /2021/
• what: The authors show the experimental results compared with the baseline methods. In the experiments , the authors focused on the cooperation between the predators rather than the competition between the predators and prey. As illustrated in Figure 5, the authors show the results in terms of the 0-1 normalized mean predator score . . .
  

   

  

  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.