ICML
1999
IEEE
15 years 7 days ago
1999
IEEE
Many interesting problems, such as power grids, network switches, and tra c ow, that are candidates for solving with reinforcement learningRL, alsohave properties that make distri...
ICML
2000
IEEE
15 years 7 days ago
2000
IEEE
This paper presents a general method to derive tight rates of convergence for numerical approximations in optimal control when we consider variable resolution grids. We study the ...
ICML
2009
IEEE
15 years 7 days ago
2009
IEEE
We consider the problem of estimating the policy gradient in Partially Observable Markov Decision Processes (POMDPs) with a special class of policies that are based on Predictive ...