Sciweavers

2100 search results - page 136 / 420
» Observation Can Be as Effective as Action in Problem Solving
Sort
View
ATAL
2005
Springer
15 years 12 months ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson
AIPS
2009
15 years 7 months ago
Computing Robust Plans in Continuous Domains
We define the robustness of a sequential plan as the probability that it will execute successfully despite uncertainty in the execution environment. We consider a rich notion of u...
Christian Fritz, Sheila A. McIlraith
GECCO
2008
Springer
143views Optimization» more  GECCO 2008»
15 years 7 months ago
Collective intelligence and bush fire spotting
Bush fires cause major damage each year in many areas of the world and the earlier that they can be detected the easier it is to minimize this damage. This paper describes a coll...
David Howden, Tim Hendtlass
AAAI
2006
15 years 7 months ago
Decision Making in Uncertain Real-World Domains Using DT-Golog
DTGolog, a decision-theoretic agent programming language based on the situation calculus, was proposed to ease some of the computational difficulties associated with Markov Decisi...
Mikhail Soutchanski, Huy Pham, John Mylopoulos
DSN
2006
IEEE
15 years 10 months ago
An Approach for Detecting and Distinguishing Errors versus Attacks in Sensor Networks
Distributed sensor networks are highly prone to accidental errors and malicious activities, owing to their limited resources and tight interaction with the environment. Yet only a...
Claudio Basile, Meeta Gupta, Zbigniew Kalbarczyk, ...