548 search results - page 16 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
105
click to vote
IJCAI
2007
15 years 1 months ago
2007
The options framework provides a method for reinforcement learning agents to build new high-level skills. However, since options are usually learned in the same state space as the...
105
click to vote
SGAI
2004
Springer
15 years 5 months ago
2004
Springer
We introduce a new class of Reinforcement Learning algorithms designed to operate in perceptual spaces containing images. They work by classifying the percepts using a computer vi...
121
click to vote
ATAL
2005
Springer
15 years 5 months ago
2005
Springer
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
108
click to vote
ICCV
2003
IEEE
15 years 5 months ago
2003
IEEE
Relevance feedback (RF) is an interactive process which refines the retrievals by utilizing user’s feedback history. Most researchers strive to develop new RF techniques and ign...
NIPS
1994
15 years 1 months ago
1994
To appear in: G. Tesauro, D. S. Touretzky and T. K. Leen, eds., Advances in Neural Information Processing Systems 7, MIT Press, Cambridge MA, 1995. A straightforward approach to t...