3084 search results - page 232 / 617 » Learning to Take Actions |
166
click to vote
IJCAI
1997
15 years 8 months ago
1997
Many of the challenges faced by the £eld of Computational Intelligence in building intelligent agents, involve determining mappings between numerous and varied sensor inputs and ...
186
click to vote
AIPS
2008
15 years 9 months ago
2008
Enforced hill-climbing is an effective deterministic hillclimbing technique that deals with local optima using breadth-first search (a process called "basin flooding"). ...
184
click to vote
JACM
2006
15 years 6 months ago
2006
"Experts algorithms" constitute a methodology for choosing actions repeatedly, when the rewards depend both on the choice of action and on the unknown current state of t...
178
click to vote
ICML
2006
IEEE
16 years 7 months ago
2006
IEEE
Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms co...
182
click to vote
ICML
2004
IEEE
16 years 1 days ago
2004
IEEE
The paper is concerned with two-class active learning. While the common approach for collecting data in active learning is to select samples close to the classification boundary,...