2011 search results - page 1 / 403 » Universal Reinforcement Learning |
CORR
2007
Springer
13 years 11 months ago
2007
Springer
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...
CAEPIA
2011
Springer
12 years 11 months ago
2011
Springer
In this paper we apply the recent notion of anytime universal intelligence tests to the evaluation of a popular reinforcement learning algorithm, Q-learning. We show that a general...
AGI
2011
13 years 2 months ago
2011
We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intra...
ICML
2004
IEEE
14 years 11 months ago
2004
IEEE
lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
JSW
2007
13 years 10 months ago
2007
— This paper describes the importance of new skilled architects in the discipline of Software and Enterprise Architecture. Architects are often idealized as super heroes with a l...