Transfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 1041-1045.
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.
@inproceedings{ijcai2007p168,
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 = {Proceedings of the Twentieth International Joint Conference on
Artificial Intelligence, {IJCAI-07}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ramon López de Mántaras},
pages = {1041--1045},
year = {2007},
url = {https://ijcai.org/proceedings/2007/168},
}
TY - CPAPER TI - Transfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL AU - Sharma, Manu AU - Holmes, Michael P. AU - Santamaría, Juan Carlos AU - Irani, Arya AU - Jr., Charles Lee Isbell AU - Ram, Ashwin T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 SP - 1041 EP - 1045 UR - https://ijcai.org/proceedings/2007/168 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
