Sciweavers

206 search results - page 32 / 42
» Learning Heuristic Functions from Relaxed Plans
Sort
View
JMLR
2010
148views more  JMLR 2010»
14 years 4 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
TASE
2008
IEEE
14 years 9 months ago
An Optimization-Based Approach for Design Project Scheduling
Concurrent engineering has been widely used in managing design projects to speed up the design process by concurrently performing multiple tasks. Since the progress of a design tas...
Ming Ni, Peter B. Luh, Bryan Moser
GECCO
2010
Springer
244views Optimization» more  GECCO 2010»
14 years 10 months ago
Implicit fitness and heterogeneous preferences in the genetic algorithm
This paper takes an economic approach to derive an evolutionary learning model based entirely on the endogenous employment of genetic operators in the service of self-interested a...
Justin T. H. Smith
ICML
2010
IEEE
14 years 11 months ago
Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multiarmed bandit problem, where the payoff function is ...
Niranjan Srinivas, Andreas Krause, Sham Kakade, Ma...
AIPS
2003
14 years 11 months ago
Reasoning about Autonomous Processes in an Estimated-Regression Planner
We examine the issues that arise in extending an estimatedregression (ER) planner to reason about autonomous processes that run and have continuous and discrete effects without th...
Drew V. McDermott