Sciweavers

1126 search results - page 187 / 226
» Personal Navigating Agents
Sort
View
JAIR
2011
144views more  JAIR 2011»
15 years 1 months ago
Non-Deterministic Policies in Markovian Decision Processes
Markovian processes have long been used to model stochastic environments. Reinforcement learning has emerged as a framework to solve sequential planning and decision-making proble...
Mahdi Milani Fard, Joelle Pineau
AI
2011
Springer
14 years 10 months ago
Decentralized MDPs with sparse interactions
In this work, we explore how local interactions can simplify the process of decision-making in multiagent systems, particularly in multirobot problems. We review a recent decision-...
Francisco S. Melo, Manuela M. Veloso
AIPS
2011
14 years 10 months ago
Planning to Perceive: Exploiting Mobility for Robust Object Detection
Consider the task of a mobile robot autonomously navigating through an environment while detecting and mapping objects of interest using a noisy object detector. The robot must re...
Javier Vélez, Garrett Hemann, Albert S. Hua...
HCI
2009
15 years 4 months ago
Acquiring a Physical World and Serving Its Mirror World Simultaneously
A mirror world, which is a virtual space modeling a physical space, attracts enormous interests from VR community recently. Various applications such as Second Life, Google Earth a...
Sengpyo Hong, Jong-gil Ahn, Heedong Ko, Jinwook Ki...
IAT
2009
IEEE
16 years 1 months ago
Evaluating a Drama Management Approach in an Interactive Fiction Game
— In this paper, we evaluate a drama management approach deployed in an implementation of a graphical interactive fiction game. Our approach uses players’ feedback as a basis f...
Andrea Corradini, Manish Mehta, Santi Ontañ...