Add to ORKGStochastic Shortest Path problems (SSPs), a subclass of Markov Decision Problems (MDPs), can be efficiently dealt with using Real-Time Dynamic Programming (RTDP). Yet, MDP models are often uncertain (obtained through statistics or guessing). The usual approach is robust planning: searching for the best policy under the worst model. This paper shows how RTDP can be made robust in the common case where transition probabilities are known to lie in a given interval.
We present a method for designing a robust control policy for an uncertain system subject to tempora...
In many probabilistic planning scenarios, a system’s behavior needs to not only maximize the expecte...
Environment models are not always known a priori, and approximating stochastic transition dynamics m...
Stochastic Shortest Path problems (SSPs), a sub-class of Markov Decision Problems (MDPs), can be eff...
Stochastic Shortest Path problems (SSPs), a subclass of Markov Decision Problems (MDPs), can be effi...
Stochastic Shortest Path problems (SSPs) can be efficiently dealt with by the Real-Time Dynamic Prog...
Stochastic Shortest Path problems (SSPs) can be efficiently dealt with by the Real-Time Dynamic Prog...
We present a modification of the Real-Time Dynamic Programming (rtdp) algorithm that makes it a ge...
International audienceStochastic Shortest Path problems (SSPs) can be efficiently dealt with by the ...
We consider large-scale Markov decision processes (MDPs) with parameter un-certainty, under the robu...
MDPs are an attractive formalization for planning, but realistic problems often have intractably lar...
Large real-world Probabilistic Temporal Planning (PTP) is a very challenging research field. A comm...
The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs...
The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs...
We consider large-scale Markov decision pro-cesses (MDPs) with parameter uncertainty, un-der the rob...
We present a method for designing a robust control policy for an uncertain system subject to tempora...
In many probabilistic planning scenarios, a system’s behavior needs to not only maximize the expecte...
Environment models are not always known a priori, and approximating stochastic transition dynamics m...
Stochastic Shortest Path problems (SSPs), a sub-class of Markov Decision Problems (MDPs), can be eff...
Stochastic Shortest Path problems (SSPs), a subclass of Markov Decision Problems (MDPs), can be effi...
Stochastic Shortest Path problems (SSPs) can be efficiently dealt with by the Real-Time Dynamic Prog...
Stochastic Shortest Path problems (SSPs) can be efficiently dealt with by the Real-Time Dynamic Prog...
We present a modification of the Real-Time Dynamic Programming (rtdp) algorithm that makes it a ge...
International audienceStochastic Shortest Path problems (SSPs) can be efficiently dealt with by the ...
We consider large-scale Markov decision processes (MDPs) with parameter un-certainty, under the robu...
MDPs are an attractive formalization for planning, but realistic problems often have intractably lar...
Large real-world Probabilistic Temporal Planning (PTP) is a very challenging research field. A comm...
The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs...
The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs...
We consider large-scale Markov decision pro-cesses (MDPs) with parameter uncertainty, un-der the rob...
We present a method for designing a robust control policy for an uncertain system subject to tempora...
In many probabilistic planning scenarios, a system’s behavior needs to not only maximize the expecte...
Environment models are not always known a priori, and approximating stochastic transition dynamics m...