4 search results - page 1 / 1 » Predictive representations for policy gradient in POMDPs |
ICML
2009
IEEE
14 years 5 months 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 ...
IJCAI
2007
13 years 6 months ago
2007
Most work on Predictive Representations of State (PSRs) has focused on learning and planning in unstructured domains (for example, those represented by flat POMDPs). This paper e...
IJCAI
2003
13 years 6 months ago
2003
We address the problem of optimally controlling stochastic environments that are partially observable. The standard method for tackling such problems is to define and solve a Part...
AAAI
2006
13 years 6 months ago
2006
Planning in partially-observable dynamical systems is a challenging problem, and recent developments in point-based techniques such as Perseus significantly improve performance as...