neural networks research group
areas
people
projects
demos
publications
software/data
Model-based Reinforcement Learning in a Complex Domain (2008)
Shivaram Kalyanakrishnan
and
Peter Stone
and
Yaxin Liu
Reinforcement learning is a paradigm under which an agent seeks to improve its policy by making learning updates based on the experiences it gathers through interaction with the environment. emphModel-free algorithms perform updates solely bas ed on observed experiences. By contrast, emphmodel-based algorithms learn a model of the environment that effectively simulates its dynamics. The model may be used to simulate experiences or to plan into the future, potentially expediting the learning process. This paper presents a model-based reinforcement learning approach for Keepaway, a complex, continuous, stochastic, multiagent subtask of RoboCup simulated soccer. First, we propose the design of an environmental model that is partly learned based on the agent's experiences. This model is then coupled with the reinforcement learning algorithm to learn an action selection policy. We evaluate our method through empirical comparisons with model-free approaches that have been previously applied successfully to this task. Results demonstrate significant gains in the learning speed and asymptotic performance of our method. We also show that the learned model can be used effectively as part of a planning-based approach with a hand-coded policy.
View:
PDF
,
PS
,
HTML
Citation:
In Ubbo Visser and Fernando Ribeiro and Takeshi Ohashi and Frank Dellaert, editors,
RoboCup-2007: Robot Soccer World Cup XI
, Lecture Notes in Artificial Intelligence, 5001, 171-83, Berlin, 2008. Springer Verlag.
Bibtex:
@incollection{LNAI2007-shivaram, title={Model-based Reinforcement Learning in a Complex Domain}, author={Shivaram Kalyanakrishnan and Peter Stone and Yaxin Liu}, booktitle={RoboCup-2007: Robot Soccer World Cup XI}, volume={5001}, editor={Ubbo Visser and Fernando Ribeiro and Takeshi Ohashi and Frank Dellaert}, series={Lecture Notes in Artificial Intelligence}, address={Berlin}, publisher={Springer Verlag}, pages={171-83}, url="http://nn.cs.utexas.edu/?LNAI2007-shivaram", year={2008} }
People
Shivaram Kalyanakrishnan
shivaram [at] cs utexas edu
Yaxin Liu
Peter Stone
pstone [at] cs utexas edu
Areas of Interest
Simulated Robot Soccer
Reinforcement Learning
Other Areas