Accelerating Multiagent Reinforcement Learning Through Transfer Learning
Abstract
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.
Cite
Text
da Silva and Costa. "Accelerating Multiagent Reinforcement Learning Through Transfer Learning." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.10518Markdown
[da Silva and Costa. "Accelerating Multiagent Reinforcement Learning Through Transfer Learning." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/dasilva2017aaai-accelerating/) doi:10.1609/AAAI.V31I1.10518BibTeX
@inproceedings{dasilva2017aaai-accelerating,
title = {{Accelerating Multiagent Reinforcement Learning Through Transfer Learning}},
author = {da Silva, Felipe Leno and Costa, Anna Helena Reali},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2017},
pages = {5034-5035},
doi = {10.1609/AAAI.V31I1.10518},
url = {https://mlanthology.org/aaai/2017/dasilva2017aaai-accelerating/}
}