Sciweavers

754 search results - page 102 / 151
» Learning executable agent behaviors from observation
Sort
View
ECML
2004
Springer
15 years 9 months ago
Analyzing Multi-agent Reinforcement Learning Using Evolutionary Dynamics
In this paper, we show how the dynamics of Q-learning can be visualized and analyzed from a perspective of Evolutionary Dynamics (ED). More specifically, we show how ED can be use...
Pieter Jan't Hoen, Karl Tuyls
AAI
2008
101views more  AAI 2008»
15 years 4 months ago
A Replanning Algorithm for Decision Theoretic Hierarchical Planning: Principles and Empirical Evaluation
In this paper, we present a replanning algorithm for a decision-theoretic hierarchical planner, illustrate the experimental methodology we designed to investigate its performance,...
Guido Boella, Rossana Damiano
ICECCS
2005
IEEE
236views Hardware» more  ICECCS 2005»
15 years 10 months ago
Detecting Malicious JavaScript Code in Mozilla
The JavaScript language is used to enhance the clientside display of web pages. JavaScript code is downloaded into browsers and executed on-the-fly by an embedded interpreter. Br...
Oystein Hallaraker, Giovanni Vigna
GROUP
2005
ACM
15 years 10 months ago
Follow the (slash) dot: effects of feedback on new members in an online community
Many virtual communities involve ongoing discussions, with large numbers of users and established, if implicit rules for participation. As new users enter communities like this, b...
Cliff Lampe, Erik W. Johnston
JAIR
2011
187views more  JAIR 2011»
14 years 11 months ago
A Monte-Carlo AIXI Approximation
This paper describes a computationally feasible approximation to the AIXI agent, a universal reinforcement learning agent for arbitrary environments. AIXI is scaled down in two ke...
Joel Veness, Kee Siong Ng, Marcus Hutter, William ...