113 search results - page 17 / 23 » Learning Representation and Control in Continuous Markov Dec... |
117
click to vote
ICML
2007
IEEE
16 years 5 months ago
2007
IEEE
Basis functions derived from an undirected graph connecting nearby samples from a Markov decision process (MDP) have proven useful for approximating value functions. The success o...
126
click to vote
AIPS
2007
15 years 6 months ago
2007
In sequential decision-making problems formulated as Markov decision processes, state-value function approximation using domain features is a critical technique for scaling up the...
183
click to vote
FORMATS
2010
Springer
15 years 2 months ago
2010
Springer
We present a general approach to combine symbolic state space representations for the discrete and continuous parts in the synthesis of winning strategies for timed reachability ga...
133
click to vote
ICML
2003
IEEE
16 years 5 months ago
2003
IEEE
We investigate methods for planning in a Markov Decision Process where the cost function is chosen by an adversary after we fix our policy. As a running example, we consider a rob...
150
click to vote
CORR
2010
Springer
15 years 3 months ago
2010
Springer
In this report, we consider the problem of real-time transmission scheduling over time-varying channels. We first formulate the transmission scheduling problem as a Markov decisio...