CQL_Ollington_2003.pdf (239.43 kB)
Concurrent Q-Learning for Autonomous Mapping and Navigation
conference contribution
posted on 2023-05-26, 09:42 authored by Ollington, R, Vamplew, PThis paper presents a new algorithm for goal-independent Q-learning. The model was tested on a simulation of the Morris watermaze task. The new model learns faster than conventional Q-learning and experiences no interference when the goal location is moved. Once the new location has been discovered the system is able to navigate directly to the platform on subsequent trials. The model was also tested on watermaze tasks involving barriers. The presence of barriers did not affect the acquisition of "one-trial" learning. While presented as a navigational and mapping technique, the model could be applied to any reinforcement learning task with a variable reward structure.
History
Department/School
School of ComputingPublication status
- Published
Event title
The 2nd International Conference on Computational Intelligence, Robotics and Autonomous SystemsEvent Venue
SingaporeDate of Event (Start Date)
2003-12-15Date of Event (End Date)
2003-12-18Repository Status
- Open
Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC