Sciweavers

360 search results - page 5 / 72
» Combining Learned Discrete and Continuous Action Models
Sort
View
116
Voted
ABIALS
2008
Springer
14 years 11 months ago
Multiscale Anticipatory Behavior by Hierarchical Reinforcement Learning
Abstract. In order to establish autonomous behavior for technical systems, the well known trade-off between reactive control and deliberative planning has to be considered. Within ...
Matthias Rungger, Hao Ding, Olaf Stursberg
GECCO
2007
Springer
179views Optimization» more  GECCO 2007»
15 years 3 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, ...
ECML
2007
Springer
15 years 3 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
JAIR
2006
122views more  JAIR 2006»
14 years 9 months ago
Solving Factored MDPs with Hybrid State and Action Variables
Efficient representations and solutions for large decision problems with continuous and discrete variables are among the most important challenges faced by the designers of automa...
Branislav Kveton, Milos Hauskrecht, Carlos Guestri...
JAIR
2006
110views more  JAIR 2006»
14 years 9 months ago
Modelling Mixed Discrete-Continuous Domains for Planning
In this paper we present pddl+, a planning domain description language for modelling mixed discrete-continuous planning domains. We describe the syntax and modelling style of pddl...
Maria Fox, Derek Long