Hierarchical multi-agent reinforcement learning

13 years 12 months ago
Hierarchical multi-agent reinforcement learning
In this paper, we investigate the use of hierarchical reinforcement learning (HRL) to speed up the acquisition of cooperative multi-agent tasks. We introduce a hierarchical multi-agent reinforcement learning (RL) framework, and propose a hierarchical multi-agent RL algorithm called Cooperative HRL. In this framework, agents are cooperative and homogeneous (use the same task decomposition). Learning is decentralized, with each agent learning three interrelated skills: how to perform each individual subtask, the order in which to carry them out, and how to coordinate with other agents. We define cooperative subtasks to be those subtasks in which coordination among agents significantly improves the performance of the overall task. Those levels of the hierarchy which include cooperative subtasks are called cooperation levels. A fundamental property of the proposed approach is that it allows agents to learn coordination faster by sharing information at the level of cooperative subtasks, r...
Rajbala Makar, Sridhar Mahadevan, Mohammad Ghavamz
Added 28 Jul 2010
Updated 28 Jul 2010
Type Conference
Year 2001
Authors Rajbala Makar, Sridhar Mahadevan, Mohammad Ghavamzadeh
Comments (0)