Sciweavers

ATAL
2003
Springer
13 years 8 months ago
Coordination in multiagent reinforcement learning: a Bayesian approach
Much emphasis in multiagent reinforcement learning (MARL) research is placed on ensuring that MARL algorithms (eventually) converge to desirable equilibria. As in standard reinfor...
Georgios Chalkiadakis, Craig Boutilier
STACS
2004
Springer
13 years 9 months ago
Digraphs Exploration with Little Memory
Under the robot model, we show that a robot needs Ω(n log d) bits of memory to perform exploration of digraphs with n nodes and maximum out-degree d. We then describe an algorith...
Pierre Fraigniaud, David Ilcinkas
SAMOS
2004
Springer
13 years 9 months ago
Constraints Derivation and Propagation for Large-Scale Embedded Systems Exploration
Abstract— The translation of user requirements to system constraints and parameters during an exploration exercise is a hard problem, especially in the context of large scale emb...
Laurentiu Nicolae, Ed F. Deprettere
EKAW
2004
Springer
13 years 9 months ago
A Topic-Based Browser for Large Online Resources
The exploration of large information spaces is a difficult task, especially if the user is not familiar with the terminology used to describe information. Conceptual models of a do...
Heiner Stuckenschmidt, Anita de Waard, Ravinder Bh...
ICRA
2005
IEEE
118views Robotics» more  ICRA 2005»
13 years 9 months ago
Stable Exploration for Bearings-only SLAM
— Recent work on robotic exploration and active sensing has examined a variety of information-theoretic approaches to efficient and convergent map construction. These involve mo...
Robert Sim
ICRA
2005
IEEE
111views Robotics» more  ICRA 2005»
13 years 9 months ago
Single-Query Entropy-Guided Path Planning
Motion planning for robots with many degrees of freedom requires the exploration of an exponentially large configuration space. Single-query motion planners restrict exploration ...
Brendan Burns, Oliver Brock
ICRA
2006
IEEE
131views Robotics» more  ICRA 2006»
13 years 9 months ago
Using Reinforcement Learning to Improve Exploration Trajectories for Error Minimization
Abstract— The mapping and localization problems have received considerable attention in robotics recently. The exploration problem that drives mapping has started to generate sim...
Thomas Kollar, Nicholas Roy
CSMR
2006
IEEE
13 years 9 months ago
Package Patterns for Visual Architecture Recovery
Recovering the architecture is the first step towards reengineering a software system. Many reverse engineering tools use top-down exploration as a way of providing a visual and ...
Mircea Lungu, Michele Lanza, Tudor Gîrba
SMC
2007
IEEE
102views Control Systems» more  SMC 2007»
13 years 10 months ago
An improved immune Q-learning algorithm
—Reinforcement learning is a framework in which an agent can learn behavior without knowledge on a task or an environment by exploration and exploitation. Striking a balance betw...
Zhengqiao Ji, Q. M. Jonathan Wu, Maher A. Sid-Ahme...
ICRA
2008
IEEE
112views Robotics» more  ICRA 2008»
13 years 10 months ago
Balancing exploration and exploitation in motion planning
— Computationally efficient motion planning must avoid exhaustive exploration of configuration space. We argue that this can be accomplished most effectively by carefully balan...
Markus Rickert, Oliver Brock, Alois Knoll