40 search results - page 1 / 8 » Parametric regret in uncertain Markov decision processes |
CDC
2009
IEEE
13 years 9 months ago
2009
IEEE
— We consider decision making in a Markovian setup where the reward parameters are not known in advance. Our performance criterion is the gap between the performance of the best ...
AAAI
2010
13 years 6 months ago
2010
The precise specification of reward functions for Markov decision processes (MDPs) is often extremely difficult, motivating research into both reward elicitation and the robust so...
ALT
2008
Springer
14 years 1 months ago
2008
Springer
Abstract. We consider an upper confidence bound algorithm for Markov decision processes (MDPs) with deterministic transitions. For this algorithm we derive upper bounds on the onl...
EWRL
2008
13 years 6 months ago
2008
Abstract. We consider a control problem where the decision maker interacts with a standard Markov decision process with the exception that the reward functions vary arbitrarily ove...
ICML
2007
IEEE
14 years 5 months ago
2007
IEEE
Markov decision processes are an effective tool in modeling decision-making in uncertain dynamic environments. Since the parameters of these models are typically estimated from da...