Loading...

Critic learning in multi agent credit assignment problem

Rahaie, Z ; Sharif University of Technology | 2016

573 Viewed
  1. Type of Document: Article
  2. DOI: 10.3233/IFS-162093
  3. Publisher: IOS Press , 2016
  4. Abstract:
  5. Multi-agent systems can be seen as an apparatus for testing the performance of real distributed systems. One problem encountered in multi-agent systems with the learning capability is credit assignment. This paper presents two methods for solving this problem. The first method assigns credit to the agents according to the history of the interaction while the second method assigns credit to the agents according to the knowledge of agents, and thus the shares of the agents are extracted from the feedback of the environment. The computer experiments show that critic learning has a positive impact in credit assignment problem
  6. Keywords:
  7. Credit assignment ; Multi-agent systems ; Combinatorial optimization ; History ; Problem solving ; Reinforcement learning ; Computer experiment ; Credit assignment ; Credit assignment problems ; Interaction ; Knowledge ; Learning capabilities ; Multi agent ; Real distributed systems ; Multi agent systems
  8. Source: Journal of Intelligent and Fuzzy Systems ; Volume 30, Issue 6 , 2016 , Pages 3465-3480 ; 10641246 (ISSN)
  9. URL: https://content.iospress.com/articles/journal-of-intelligent-and-fuzzy-systems/ifs2093