AAAI Publications, Thirty-First AAAI Conference on Artificial Intelligence

Font Size: 
Accelerating Multiagent Reinforcement Learning through Transfer Learning
Felipe Leno da Silva, Anna Helena Reali Costa

Last modified: 2017-02-12


Reinforcement Learning (RL) is a widely used solution for sequential decision-making problems and has been used in many complex domains. However, RL algorithms suffer from scalability issues, especially when multiple agents are acting in a shared environment. This research intends to accelerate learning in multiagent sequential decision-making tasks by reusing previous knowledge, both from past solutions and advising between agents. We intend to contribute a Transfer Learning framework focused on Multiagent RL, requiring as few domain-specific hand-coded parameters as possible.


Transfer Learning; Reinforcement Learning; Multiagent Systems

Full Text: PDF