Next:
Introduction
Up:
Learning Evaluation Functions
Previous:
Learning Evaluation Functions
Contents
Introduction
Background
Proposal
Value Function Approximation for Prediction and Control
Markov Decision Problems
Literature Review
VFA in Acyclic Domains: ``ROUT''
Value Function Approximation for Combinatorial Optimization
Combinatorial Optimization
Optimization as an MDP
Prediction for Optimization: ``STAGE''
Direct Meta-Optimization of Evaluation Functions
Literature Review
Meta-Optimization Algorithms
Application Domains
VLSI Channel Routing
Radiotherapy Treatment Planning
Scheduling a Factory Production Line
Spacecraft Configuration Optimization
Backgammon Move Selection
Summary
Contributions
Timeline
Algorithms
TD(
) for Control
ROUT
STAGE
Preliminary Results
ROUT
STAGE
References
About this document ...
Justin A. Boyan
Sat Jun 22 20:49:48 EDT 1996
) for Control