Sciweavers

8838 search results - page 1365 / 1768
» Generalizing Domain Theory
Sort
View
ECML
2007
Springer
16 years 1 months ago
Policy Gradient Critics
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
Daan Wierstra, Jürgen Schmidhuber
FPGA
2007
ACM
119views FPGA» more  FPGA 2007»
16 years 1 months ago
Synthesis of an application-specific soft multiprocessor system
The application-specific multiprocessor System-on-a-Chip is a promising design alternative because of its high degree of flexibility, short development time, and potentially high ...
Jason Cong, Guoling Han, Wei Jiang
GECCO
2007
Springer
179views Optimization» more  GECCO 2007»
16 years 1 months ago
XCSF with computed continuous action
Wilson introduced XCSF as a successor to XCS. The major development of XCSF is the concept of a computed prediction. The efficiency of XCSF in dealing with numerical input and con...
Trung Hau Tran, Cédric Sanza, Yves Duthen, ...
GECCO
2007
Springer
172views Optimization» more  GECCO 2007»
16 years 1 months ago
Improving the human readability of features constructed by genetic programming
The use of machine learning techniques to automatically analyse data for information is becoming increasingly widespread. In this paper we examine the use of Genetic Programming a...
Matthew Smith, Larry Bull
163
Voted
GECCO
2007
Springer
156views Optimization» more  GECCO 2007»
16 years 1 months ago
A phenotypic analysis of GP-evolved team behaviours
This paper presents an approach to analyse the behaviours of teams of autonomous agents who work together to achieve a common goal. The agents in a team are evolved together using...
Darren Doherty, Colm O'Riordan
« Prev « First page 1365 / 1768 Last » Next »