DIS
2007
Springer
14 years 11 months ago
2007
Springer
In this paper, we propose a new concept, thinning-out, for reducing the number of trials in skill discovery. Thinning-out means to skip over such trials that are unlikely to improv...
80
Voted
ICML
2006
IEEE
15 years 10 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...