Sciweavers

683 search results - page 52 / 137
» Coarticulation in Markov Decision Processes
Sort
View
ICRA
2007
IEEE
126views Robotics» more  ICRA 2007»
16 years 13 days ago
A formal framework for robot learning and control under model uncertainty
— While the Partially Observable Markov Decision Process (POMDP) provides a formal framework for the problem of robot control under uncertainty, it typically assumes a known and ...
Robin Jaulmes, Joelle Pineau, Doina Precup
ICML
2006
IEEE
16 years 2 days ago
Automatic basis function construction for approximate dynamic programming and reinforcement learning
We address the problem of automatically constructing basis functions for linear approximation of the value function of a Markov Decision Process (MDP). Our work builds on results ...
Philipp W. Keller, Shie Mannor, Doina Precup
AAAI
1994
15 years 7 months ago
Acting Optimally in Partially Observable Stochastic Domains
In this paper, we describe the partially observable Markov decision process pomdp approach to nding optimal or near-optimal control strategies for partially observable stochastic ...
Anthony R. Cassandra, Leslie Pack Kaelbling, Micha...
ICML
2006
IEEE
16 years 7 months ago
Qualitative reinforcement learning
When the transition probabilities and rewards of a Markov Decision Process are specified exactly, the problem can be solved without any interaction with the environment. When no s...
Arkady Epshteyn, Gerald DeJong
ICML
2006
IEEE
16 years 7 months ago
PAC model-free reinforcement learning
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...