548 search results - page 15 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
ICML
2002
IEEE
16 years 15 days ago
2002
IEEE
Two notions of optimality have been explored in previous work on hierarchical reinforcement learning (HRL): hierarchical optimality, or the optimal policy in the space defined by ...
ICML
2005
IEEE
16 years 15 days ago
2005
IEEE
We introduce flexible algorithms that can automatically learn mappings from images to actions by interacting with their environment. They work by introducing an image classifier i...
101
click to vote
CG
2000
Springer
15 years 4 months ago
2000
Springer
Abstract. Over the years, various research projects have attempted to develop a chess program that learns to play well given little prior knowledge beyond the rules of the game. Ea...
100
click to vote
EUROCAST
2007
Springer
15 years 5 months ago
2007
Springer
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
123
click to vote
AI
2002
Springer
14 years 11 months ago
2002
Springer
Learning to act in a multiagent environment is a difficult problem since the normal definition of an optimal policy no longer applies. The optimal policy at any moment depends on ...