Sciweavers

280 search results - page 46 / 56
» Planning for Markov Decision Processes with Sparse Stochasti...
Sort
View
ICRA
2010
IEEE
133views Robotics» more  ICRA 2010»
14 years 8 months ago
Variable resolution decomposition for robotic navigation under a POMDP framework
— Partially Observable Markov Decision Processes (POMDPs) offer a powerful mathematical framework for making optimal action choices in noisy and/or uncertain environments, in par...
Robert Kaplow, Amin Atrash, Joelle Pineau
IJRR
2011
218views more  IJRR 2011»
14 years 4 months ago
Motion planning under uncertainty for robotic tasks with long time horizons
Abstract Partially observable Markov decision processes (POMDPs) are a principled mathematical framework for planning under uncertainty, a crucial capability for reliable operation...
Hanna Kurniawati, Yanzhu Du, David Hsu, Wee Sun Le...
NIPS
2008
14 years 11 months ago
MDPs with Non-Deterministic Policies
Markov Decision Processes (MDPs) have been extensively studied and used in the context of planning and decision-making, and many methods exist to find the optimal policy for probl...
Mahdi Milani Fard, Joelle Pineau
AIPS
2000
14 years 11 months ago
On-line Scheduling via Sampling
1 We consider the problem of scheduling an unknown sequence of tasks for a single server as the tasks arrive with the goal off maximizing the total weighted value of the tasks serv...
Hyeong Soo Chang, Robert Givan, Edwin K. P. Chong
ECML
2007
Springer
15 years 4 months ago
Policy Gradient Critics
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
Daan Wierstra, Jürgen Schmidhuber