4035 search results - page 302 / 807 » Useless Actions Are Useful |
167
click to vote
ICML
2010
IEEE
15 years 7 months ago
2010
IEEE
We consider approximate policy evaluation for finite state and action Markov decision processes (MDP) in the off-policy learning context and with the simulation-based least square...
168
click to vote
AIPS
2010
15 years 6 months ago
2010
When using a planner-based agent architecture, many things can go wrong. First and foremost, an agent might fail to execute one of the planned actions for some reasons. Even more ...
165
Voted
CORR
2010
Springer
15 years 6 months ago
2010
Springer
Markov decision processes (MDPs) are widely used for modeling decision-making problems in robotics, automated control, and economics. Traditional MDPs assume that the decision mak...
189
Voted
ENTCS
2008
15 years 6 months ago
2008
We do not interact with systems without first performing some physical action on a physical device. This paper shows how formal notations and formal models can be developed to acc...
177
click to vote
ENGL
2006
15 years 6 months ago
2006
A direct adaptive neural network control system with and without integral action term is designed for the general class of continuous biological fermentation processes. The control...