2011 search results - page 1 / 403 » Universal Reinforcement Learning |
CORR
2007
Springer
13 years 4 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 4 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
12 years 8 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 5 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 4 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...