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 multi-layered 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, 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.
Read the paper:
Transfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL
by Manu Sharma, Michael Holmes, Juan Santamaria, Arya Irani, Charles Isbell, Ashwin Ram
International Joint Conference on Artificial Intelligence (IJCAI-07), Hyderabad, India, January 2007www.cc.gatech.edu/faculty/ashwin/papers/er-07-01.pdf
Posted by santi on October 13, 2009 at 5:29 pm
Alex J. Champandard, from AIGameDev.com, overviewed this paper, discussing its applicability to real games: aigamedev.com/theory/transfer-learning-rts
Posted by Case-Based Reasoning VS Reinforcement Learning – Part 1 – Introduction « Omar's Brain on February 14, 2010 at 4:45 am
[…] needs RL techniques in the revising phase. Q-learning is used in this paper: “Transfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL -2007″ , and another example is the master “A CBR/RL system for learning micromanagement in […]