448 search results - page 59 / 90 » Abstraction in Predictive State Representations |
PKDD
2009
Springer
15 years 4 months ago
2009
Springer
Abstract. Feature selection in reinforcement learning (RL), i.e. choosing basis functions such that useful approximations of the unkown value function can be obtained, is one of th...
DNA
2007
Springer
15 years 4 months ago
2007
Springer
Abstract. A major challenge in nanoscience is the design of synthetic molecular devices that run autonomously and are programmable. DNA-based synthetic molecular devices have the a...
CEEMAS
2005
Springer
15 years 3 months ago
2005
Springer
Abstract. We discuss the application of Model-Based Diagnosis in (agentbased) planning. Here, a plan together with its executing agent is considered as a system to be diagnosed. It...
EUROGP
2005
Springer
15 years 3 months ago
2005
Springer
Abstract. A protein is a linear chain of amino acids that folds into a unique functional structure, called its native state. In this state, proteins show repeated substructures lik...
SARA
2005
Springer
15 years 3 months ago
2005
Springer
Sets of features in Markov decision processes can play a critical role ximately representing value and in abstracting the state space. Selection of features is crucial to the succe...