102 search results - page 2 / 21 » MDPs with Non-Deterministic Policies |
AIPS
2010
13 years 7 months ago
2010
Computing a good policy in stochastic uncertain environments with unknown dynamics and reward model parameters is a challenging task. In a number of domains, ranging from space ro...
IWQOS
2011
Springer
12 years 7 months ago
2011
Springer
In this paper, we address the problem of providing a service broker, which offers to prospective users a composite service with a range of different Quality of Service (QoS) class...
AICCSA
2008
IEEE
13 years 11 months ago
2008
IEEE
Time Petri nets with stopwatches not only model system/environment interactions and time constraints. They further enable modeling of suspend/resume operations in real-time system...
IJCAI
2003
13 years 6 months ago
2003
We present a new algorithm, GM-Sarsa(0), for finding approximate solutions to multiple-goal reinforcement learning problems that are modeled as composite Markov decision processe...
ATAL
2010
Springer
13 years 5 months ago
2010
Springer
Despite the recent advances in planning with MDPs, the problem of generating good policies is still hard. This paper describes a way to generate policies in MDPs by (1) determiniz...