50 search results - page 2 / 10 » Learning to Drive a Bicycle Using Reinforcement Learning and... |
NIPS
2001
13 years 7 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
FBIT
2007
IEEE
13 years 12 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 ...
ICML
2005
IEEE
14 years 6 months ago
2005
IEEE
We consider the task of driving a remote control car at high speeds through unstructured outdoor environments. We present an approach in which supervised learning is first used to...
ICML
2004
IEEE
14 years 6 months ago
2004
IEEE
We consider learning in a Markov decision process where we are not explicitly given a reward function, but where instead we can observe an expert demonstrating the task that we wa...
ICML
2005
IEEE
14 years 6 months ago
2005
IEEE
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...