199 search results - page 24 / 40 » Efficient Reinforcement Learning with Relocatable Action Mod... |
EWRL
2008
14 years 11 months ago
2008
Abstract. We consider a control problem where the decision maker interacts with a standard Markov decision process with the exception that the reward functions vary arbitrarily ove...
AAAI
2006
14 years 11 months ago
2006
We present an algorithm that derives actions' effects and preconditions in partially observable, relational domains. Our algorithm has two unique features: an expressive rela...
EPIA
1995
Springer
15 years 1 months ago
1995
Springer
Abstract. The paper introduces a reinforcement learning-based methodology for performance improvement of Intelligent Controllers. The translation interfaces of a 3-level Hierarchic...
ICML
2008
IEEE
15 years 10 months ago
2008
IEEE
We present an algorithm, HI-MAT (Hierarchy Induction via Models And Trajectories), that discovers MAXQ task hierarchies by applying dynamic Bayesian network models to a successful...
NIPS
2008
14 years 11 months ago
2008
We use graphical models and structure learning to explore how people learn policies in sequential decision making tasks. Studies of sequential decision-making in humans frequently...