Sciweavers

MOR
2008
87views more  MOR 2008»
13 years 10 months ago
On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP
We consider the average cost problem for partially observable Markov decision processes (POMDP) with finite state, observation, and control spaces. We prove that there exists an -...
Huizhen Yu, Dimitri P. Bertsekas
CORR
2007
Springer
73views Education» more  CORR 2007»
13 years 11 months ago
Universal Reinforcement Learning
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...
Vivek F. Farias, Ciamac Cyrus Moallemi, Tsachy Wei...
IOR
2008
89views more  IOR 2008»
13 years 11 months ago
Impulse Control of Brownian Motion: The Constrained Average Cost Case
When a manufacturer places repeated orders with a supplier to meet changing production requirements, he faces the challenge of finding the right balance between holding costs and ...
Melda Ormeci, J. G. Dai, John H. Vande Vate
UAI
2004
14 years 8 days ago
Discretized Approximations for POMDP with Average Cost
In this paper, we propose a new lower approximation scheme for POMDP with discounted and average cost criterion. The approximating functions are determined by their values at a fi...
Huizhen Yu, Dimitri P. Bertsekas