UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Gaussian processes for sample efficient reinforcement learning with RMAX-like exploration (2010)
Tobias Jung
and
Peter Stone
We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achieve low sample complexity. To achieve low sample complexity, since the environment is unknown, an agent must intelligently balance exploration and exploitation, and must be able to rapidly generalize from observations. While in the past a number of related sample efficient RL algorithms have been proposed, to allow theoretical analysis, mainly model-learners with weak generalization capabilities were considered. Here, we separate function approximation in the model-learner (which does require samples) from the interpolation in the planner (which does not require samples). For model-learning we apply Gaussian processes regression (GP) which is able to automatically adjust itself to the complexity of the problem (via Bayesian hyperparameter selection) and, in practice, often able to learn a highly accurate model from very little data. In addition, a GP provides a natural way to determine the uncertainty of its predictions, which allows us to implement the ``optimism in the face of uncertainty'' principle used to efficiently control exploration. Our method is evaluated on four common benchmark domains.
View:
PDF
,
PS
,
HTML
Citation:
In
Proceedings of the European Conference on Machine Learning
, September 2010.
Bibtex:
@inproceedings{ECML10-jung, title={Gaussian processes for sample efficient reinforcement learning with RMAX-like exploration}, author={Tobias Jung and Peter Stone}, booktitle={Proceedings of the European Conference on Machine Learning}, month={September}, url="http://www.cs.utexas.edu/users/ai-lab?ECML10-jung", year={2010} }
Presentation:
Slides (PDF)
People
Tobias Jung
Postdoctoral Alumni
tjung [at] ulg ac be
Peter Stone
Faculty
pstone [at] cs utexas edu
Areas of Interest
Machine Learning
Reinforcement Learning
Labs
Learning Agents