126 search results - page 10 / 26 » Reinforcement Learning for Platform-Independent Visual Robot... |
GECCO
2004
Springer
14 years 22 days ago
2004
Springer
In recent years, the evolution of artificial neural networks or neuroevolution has brought promising results in solving difficult reinforcement learning problems. But, like standa...
IROS
2009
IEEE
14 years 2 months ago
2009
IEEE
— Partially Observable Markov Decision Processes (POMDPs) provide a rich mathematical model to handle realworld sequential decision processes but require a known model to be solv...
IROS
2007
IEEE
14 years 1 months ago
2007
IEEE
— While underactuated robotic systems are capable of energy efficient and rapid dynamic behavior, we still do not fully understand how body dynamics can be actively used for ada...
EGITALY
2011
12 years 7 months ago
2011
Recent advances in gesture recognition made the problem of controlling a humanoid robot in the most natural possible way an interesting challenge. Learning from Demonstration fie...
ECML
2006
Springer
13 years 11 months ago
2006
Springer
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...