Transfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL
Abstract
The goal of transfer learning is to use the knowledge acquired in a set of source tasks to improve performance in a related but previously unseen target task. In this paper, we present a multilayered architecture named CAse-Based Reinforcement Learner (CARL). It uses a novel combination of Case-Based Reasoning (CBR) and Reinforcement Learning (RL) to achieve transfer while playing against the Game AI across a variety of scenarios in MadRTS(TM), a commercial Real Time Strategy game. Our experiments demonstrate that CARL not only performs well on individual tasks but also exhibits significant performance gains when allowed to transfer knowledge from previous tasks.
Cite
Text
Sharma et al. "Transfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL." International Joint Conference on Artificial Intelligence, 2007.Markdown
[Sharma et al. "Transfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL." International Joint Conference on Artificial Intelligence, 2007.](https://mlanthology.org/ijcai/2007/sharma2007ijcai-transfer/)BibTeX
@inproceedings{sharma2007ijcai-transfer,
title = {{Transfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL}},
author = {Sharma, Manu and Holmes, Michael P. and Santamaría, Juan Carlos and Irani, Arya and Jr., Charles Lee Isbell and Ram, Ashwin},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2007},
pages = {1041-1046},
url = {https://mlanthology.org/ijcai/2007/sharma2007ijcai-transfer/}
}