What is the relation between multi-agent learning and reinforcement learning?

Is one a sub-field of the other? For instance, would it make sense to state that your research interest are multi-agent learning and reinforcement learning, or would that be weird as one includes most of the topics of the other?


I think there is an intersection. There are problems that are in reinforcement learning and in learning in multi-agent systems. There are problems in reinforcement learning, but not exactly in multi-agent systems. And there is learning in multi-agent systems that is not through reinforcement learning. For sort you can say: multi-agent reinforcement learning. I recommend take a look at these references:

Bu, Lucian, Robert Babu, and Bart De Schutter. "A comprehensive survey of multiagent reinforcement learning." IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 38.2 (2008): 156-172.

Busoniu, Lucian, Robert Babuska, and Bart De Schutter. "Multi-agent reinforcement learning: A survey." 2006 9th International Conference on Control, Automation, Robotics and Vision. IEEE, 2006.

| improve this answer | |
  • $\begingroup$ If you are a little bit familiar with RL, it's clear that there are RL algorithms that are not directly (or immediately) applicable to multi-agent systems, so there is no need to explain further that case. However, I think this answer would improve considerably if you can provide an example of a MAS that doesn't use RL and an example that uses RL. It would also be interesting to talk about hierarchical reinforcement learning (i.e. is HRL a multi-agent system?). $\endgroup$ – nbro May 23 at 19:35
  • $\begingroup$ Thank you very much for your answer. The comment from @nbro is also very helpful and I agree. $\endgroup$ – Ben C. May 23 at 20:14

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.