159 search results - page 2 / 32 » Module-Based Reinforcement Learning: Experiments with a Real... |
ICRA
2005
IEEE
13 years 10 months ago
2005
IEEE
— This paper presents a new reinforcement learning algorithm for accelerating acquisition of new skills by real mobile robots, without requiring simulation. It speeds up Q-learni...
CORR
2006
Springer
13 years 4 months ago
2006
Springer
We address the problem of autonomously learning controllers for visioncapable mobile robots. We extend McCallum's (1995) Nearest-Sequence Memory algorithm to allow for genera...
ICRA
2009
IEEE
13 years 11 months ago
2009
IEEE
— Our goal in this work is to make high level decisions for mobile robots. In particular, given a queue of prioritized object delivery tasks, we wish to find a sequence of actio...
IROS
2006
IEEE
13 years 10 months ago
2006
IEEE
— Recently, many researchers on humanoid robotics are interested in Quasi-Passive-Dynamic Walking (Quasi-PDW) which is similar to human walking. It is desirable that control para...
FBIT
2007
IEEE
13 years 11 months ago
2007
IEEE
The paper describes our first experiments on Reinforcement Learning to steer a real robot car. The applied method, Neural Fitted Q Iteration (NFQ) is purely data-driven based on ...