1512 search results - page 63 / 303 » Qualitative reinforcement learning |
ICML
2005
IEEE
14 years 8 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...
IJCNN
2008
IEEE
14 years 2 months ago
2008
IEEE
— Traditional approaches to integrating knowledge into neural network are concerned mainly about supervised learning. This paper presents how a family of self-organizing neural m...
GECCO
2006
Springer
13 years 11 months ago
2006
Springer
Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical com...
ICML
2005
IEEE
14 years 8 months ago
2005
IEEE
We present a new subgoal-based method for automatically creating useful skills in reinforcement learning. Our method identifies subgoals by partitioning local state transition gra...
IAT
2008
IEEE
13 years 8 months ago
2008
IEEE
TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a class of self-organizing neural networks that incorporates Temporal Difference (...