Knowledge-Based Multiagent Credit Assignment: A Study on Task Type and Critic Information

  title={Knowledge-Based Multiagent Credit Assignment: A Study on Task Type and Critic Information},
  author={Ahad Harati and Majid Nili Ahmadabadi and Babak Nadjar Araabi},
  journal={IEEE Systems Journal},
Multiagent credit assignment (MCA) is one of the major problems in the realization of multiagent reinforcement learning. Since the environment usually is not intelligent enough to qualify individual agents in a cooperative team, it is very important to develop some methods for assigning individual agents' credits when just a single team reinforcement is available. MCA cannot be solved in general cases, using a single technique. Therefore, our goal in this research is first to present a new view… CONTINUE READING
7 Extracted Citations
30 Extracted References
Similar Papers

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 30 references

Experimental analysis of knowledge based multiagent credit assignment

  • A. Harati, M. N. Ahmadabadi
  • Neural Information Processing: Research and…
  • 2004
2 Excerpts

RoboCup soccer simulator

  • The RoboCup Soccer Simulator Maintenance Group
  • (2004). [Online]. Available: http://sserver…
  • 2004
1 Excerpt

A study on credit assignment among cooperative and independent reinforcement learning agents

  • A. Harati
  • M.S. thesis, Dept. Elect. Comput. Eng., Univ…
  • 2003
3 Excerpts

A new approach to credit assignment in a team of cooperative Q-learning agents

  • A. Harati, M. N. Ahmadabadi
  • presented at the IEEE Conf. Syst., Man Cybern…
  • 2002
2 Excerpts

An analysis on the effects of reinforcement distribution in a distributed multi-agent team

  • M. A. Abbasi, M. N. Ahmadabadi, M. Asadpour
  • Proc. 4th Iranian Conf. Comput. Eng. (CSICC…
  • 2002
2 Excerpts

Similar Papers

Loading similar papers…