682 search results - page 54 / 137 » One-Counter Markov Decision Processes |
127
Voted
ICML
2006
IEEE
16 years 4 months ago
2006
IEEE
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...
119
Voted
ICML
2006
IEEE
16 years 4 months ago
2006
IEEE
How should a reinforcement learning agent act if its sole purpose is to efficiently learn an optimal policy for later use? In other words, how should it explore, to be able to exp...
120
Voted
ICRA
2007
IEEE
15 years 10 months ago
2007
IEEE
— 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 ...
164
click to vote
ICML
2006
IEEE
2006
IEEE
Automatic basis function construction for approximate dynamic programming and reinforcement learning
15 years 9 months ago
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 ...
159
click to vote
ICVS
2001
Springer
15 years 8 months ago
2001
Springer
High-level vision systems use object, scene or domain specific knowledge to interpret images. Unfortunately, this knowledge has to be acquired for every domain. This makes it diffi...