Sciweavers

606 search results - page 48 / 122
» Least-Commitment Action Selection
Sort
View
AAAI
1998
13 years 9 months ago
Bayesian Q-Learning
A central problem in learning in complex environmentsis balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of explora...
Richard Dearden, Nir Friedman, Stuart J. Russell
AAAI
1998
13 years 9 months ago
Solving Very Large Weakly Coupled Markov Decision Processes
We present a technique for computing approximately optimal solutions to stochastic resource allocation problems modeled as Markov decision processes (MDPs). We exploit two key pro...
Nicolas Meuleau, Milos Hauskrecht, Kee-Eung Kim, L...
AIPS
2009
13 years 9 months ago
Automatic Derivation of Memoryless Policies and Finite-State Controllers Using Classical Planners
Finite-state and memoryless controllers are simple action selection mechanisms widely used in domains such as videogames and mobile robotics. Memoryless controllers stand for func...
Blai Bonet, Héctor Palacios, Hector Geffner
IJVR
2007
101views more  IJVR 2007»
13 years 8 months ago
Affective Multimodal Control of Virtual
—In this paper we report about the use of computer generated affect to control body and mind of cognitively modeled virtual characters. We use the computational model of affect A...
Martin Klesen, Patrick Gebhard
INFORMATICALT
2002
154views more  INFORMATICALT 2002»
13 years 7 months ago
Adaptive Stable Control of Manipulators with Improved Adaptation Transients by Using On-line Supervision of the Free-Parameters
An adaptive control scheme for mechanical manipulators is proposed. The control loop essentially consists of a network for learning the robot's inverse dynamics and on-line ge...
Manuel de la Sen, Ana Almansa