Sciweavers

2100 search results - page 83 / 420
» Observation Can Be as Effective as Action in Problem Solving
Sort
View
AAAI
2008
13 years 11 months ago
Planning for Human-Robot Interaction Using Time-State Aggregated POMDPs
In order to interact successfully in social situations, a robot must be able to observe others' actions and base its own behavior on its beliefs about their intentions. Many ...
Frank Broz, Illah R. Nourbakhsh, Reid G. Simmons
KBSE
2007
IEEE
14 years 3 months ago
An automated approach to monitoring and diagnosing requirements
Monitoring the satisfaction of software requirements and diagnosing what went wrong in case of failure is a hard problem that has received little attention in the Software and Req...
Yiqiao Wang, Sheila A. McIlraith, Yijun Yu, John M...
DAGSTUHL
2007
13 years 10 months ago
Logical Particle Filtering
Abstract. In this paper, we consider the problem of filtering in relational hidden Markov models. We present a compact representation for such models and an associated logical par...
Luke S. Zettlemoyer, Hanna M. Pasula, Leslie Pack ...
AIPS
2008
13 years 11 months ago
Exact Dynamic Programming for Decentralized POMDPs with Lossless Policy Compression
High dimensionality of belief space in DEC-POMDPs is one of the major causes that makes the optimal joint policy computation intractable. The belief state for a given agent is a p...
Abdeslam Boularias, Brahim Chaib-draa
NIPS
2008
13 years 10 months ago
Goal-directed decision making in prefrontal cortex: a computational framework
Research in animal learning and behavioral neuroscience has distinguished between two forms of action control: a habit-based form, which relies on stored action values, and a goal...
Matthew Botvinick, James An