Sciweavers

1047 search results - page 54 / 210
» Learning the required number of agents for complex tasks
Sort
View
AAAI
1994
13 years 9 months ago
Small is Beautiful: A Brute-Force Approach to Learning First-Order Formulas
We describe a method for learning formulas in firstorder logic using a brute-force, smallest-first search. The method is exceedingly simple. It generates all irreducible well-form...
Steven Minton, Ian Underwood
IWANN
2005
Springer
14 years 1 months ago
Co-evolutionary Learning in Liquid Architectures
A large class of problems requires real-time processing of complex temporal inputs in real-time. These are difficult tasks for state-of-the-art techniques, since they require captu...
Igal Raichelgauz, Karina Odinaev, Yehoshua Y. Zeev...
PKDD
2009
Springer
181views Data Mining» more  PKDD 2009»
14 years 2 months ago
Active Learning for Reward Estimation in Inverse Reinforcement Learning
Abstract. Inverse reinforcement learning addresses the general problem of recovering a reward function from samples of a policy provided by an expert/demonstrator. In this paper, w...
Manuel Lopes, Francisco S. Melo, Luis Montesano
AAAI
2007
13 years 10 months ago
Temporal Difference and Policy Search Methods for Reinforcement Learning: An Empirical Comparison
Reinforcement learning (RL) methods have become popular in recent years because of their ability to solve complex tasks with minimal feedback. Both genetic algorithms (GAs) and te...
Matthew E. Taylor, Shimon Whiteson, Peter Stone
AGENTS
1997
Springer
13 years 12 months ago
Learning View Graphs for Robot Navigation
Abstract. We present a purely vision-based scheme for learning a topological representation of an open environment. The system represents selected places by local views of the surr...
Matthias O. Franz, Bernhard Schölkopf, Philip...