166 search results - page 5 / 34 » Safe exploration for reinforcement learning |
ICML
2002
IEEE
14 years 9 months ago
2002
IEEE
One of the central challenges in reinforcement learning is to balance the exploration/exploitation tradeoff while scaling up to large problems. Although model-based reinforcement ...
ICANN
2010
Springer
13 years 9 months ago
2010
Springer
We propose a new approach for reinforcement learning in problems with continuous actions. Actions are sampled by means of a diffusion tree, which generates samples in the continuou...
NIPS
1998
13 years 10 months ago
1998
ICRA
2008
IEEE
14 years 3 months ago
2008
IEEE
— We present a learning mechanism, Socially Guided Exploration, in which a robot learns new tasks through a combination of self-exploration and social interaction. The system’s...
ICML
2006
IEEE
14 years 9 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...