UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Towards the Application of Reinforcement Learning to Undirected Developmental Learning (2008)
Jonathan Mugan
and
Benjamin Kuipers
We consider the problem of how a learning agent in a continuous and dynamic world can autonomously learn about itself, its environment, and how to perform simple actions. In previous work we showed how an agent could learn an abstraction consisting of contingencies and distinctions. In this paper we propose a method whereby an agent using this abstraction can create its own reinforcement learning problems. The agent generates an internal signal that motivates it to move into states in which a contingency will hold. The agent then uses reinforcement learning to learn to move to those states effectively. It can then use the knowledge acquired through reinforcement learning as part of simple actions. We evaluate this work using a simulated physical agent that affects its world using two continuous motor variables and experiences its world using a set of fifteen continuous and discrete sensor variables. We show that by using this method the learning agent can autonomously generate reinforcement learning problems allowing it to do simple tasks, and we compare its performance to that of a hand-created reinforcement learner using tile coding.
View:
PDF
Citation:
In
Proceedings of the International Conference on Epigenetic Robotics (EpiRob-08)
2008.
Bibtex:
@inproceedings{Mugan-epirob-08, title={Towards the Application of Reinforcement Learning to Undirected Developmental Learning}, author={Jonathan Mugan and Benjamin Kuipers}, booktitle={Proceedings of the International Conference on Epigenetic Robotics (EpiRob-08)}, url="http://www.cs.utexas.edu/users/ai-lab?Mugan-epirob-08", year={2008} }
People
Benjamin Kuipers
Formerly affiliated Faculty
kuipers [at] cs utexas edu
Jonathan Mugan
Ph.D. Alumni
jmugan [at] cs utexas edu
Areas of Interest
Bootstrap Learning
Robotics