Sciweavers

53 search results - page 7 / 11
» Policies based on Trajectory Libraries
Sort
View
GECCO
2009
Springer
104views Optimization» more  GECCO 2009»
14 years 2 months ago
Sustaining diversity using behavioral information distance
Conventional similarity metrics used to sustain diversity in evolving populations are not well suited to sequential decision tasks. Genotypes and phenotypic structure are poor pre...
Faustino J. Gomez
AAAI
2010
13 years 9 months ago
Reinforcement Learning Via Practice and Critique Advice
We consider the problem of incorporating end-user advice into reinforcement learning (RL). In our setting, the learner alternates between practicing, where learning is based on ac...
Kshitij Judah, Saikat Roy, Alan Fern, Thomas G. Di...
ICFP
2000
ACM
14 years 10 days ago
Functional programming in C++
This paper describes FC++: a rich library supporting functional programming in C++. Prior approaches to encoding higher order functions in C++ have suffered with respect to polymo...
Brian McNamara, Yannis Smaragdakis
JMLR
2010
148views more  JMLR 2010»
13 years 2 months ago
A Generalized Path Integral Control Approach to Reinforcement Learning
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Evangelos Theodorou, Jonas Buchli, Stefan Schaal
NDSS
2003
IEEE
14 years 1 months ago
Access Control Based on Execution History
Security is a major, frequent concern in extensible software systems such as Java Virtual Machines and the Common Language Runtime. These systems aim to enable simple, classic app...
Martín Abadi, Cédric Fournet