Learning complementary multiagent behaviors: a case study

  title={Learning complementary multiagent behaviors: a case study},
  author={Shivaram Kalyanakrishnan and Peter Stone},
As machine learning is applied to increasingly complex tasks, it is likely that the diverse challenges encountered can only be addressed by combining the strengths of different learning algorithms. We examine this aspect of learning through a case study grounded in the robot soccer context. The task we consider is Keepaway, a popular benchmark for multiagent reinforcement learning from the simulation soccer domain. Whereas previous successful results in Keepaway have limited learning to an… CONTINUE READING
Highly Cited
This paper has 44 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 25 extracted citations

LearnPNP: A Tool for Learning Agent Behaviors

RoboCup • 2010
View 4 Excerpts
Highly Influenced

Overlapping layered learning

Artif. Intell. • 2018
View 2 Excerpts


Publications referenced by this paper.
Showing 1-10 of 21 references

Iscen and U . Erogul . A new perpective to the keepaway soccer : The tak

Proceedings of the Seventh International Joint Conference on Autonomous Agents and Multi – Agent Systems • 2008

Learning RoboCup-Keepaway with Kernels

Gaussian Processes in Practice • 2007
View 3 Excerpts

Analysis of an evolutionary reinforcement learning method in a multiagent domain Cooperative multi - agent learning : The state of the art

J. H. Metzen
Autonomous Agents and Multi - Agent Systems • 2005

Similar Papers

Loading similar papers…