11 years 8 months ago
Generalized Monte-Carlo Tree Search Extensions for General Game Playing
General Game Playing (GGP) agents must be capable of playing a wide variety of games skillfully. Monte-Carlo Tree Search (MCTS) has proven an effective reasoning mechanism for thi...
Hilmar Finnsson
112views more  COGCOM 2010»
13 years 3 months ago
Flexible Latching: A Biologically-Inspired Mechanism for Improving the Management of Homeostatic Goals
Controlling cognitive systems like domestic robots or intelligent assistive environments requires striking an appropriate balance between responsiveness and persistence. Basic goal...
Philipp Rohlfshagen, Joanna Bryson
142views Data Mining» more  DMIN 2009»
13 years 3 months ago
Action Selection in Customer Value Optimization: An Approach Based on Covariate-Dependent Markov Decision Processes
Typical methods in CRM marketing include action selection on the basis of Markov Decision Processes with fixed transition probabilities on the one hand, and scoring customers separ...
Angi Roesch, Harald Schmidbauer
101views Neural Networks» more  NN 2006»
13 years 6 months ago
A robot model of the basal ganglia: Behavior and intrinsic processing
The existence of multiple parallel loops connecting sensorimotor systems to the basal ganglia has given rise to proposals that these nuclei serve as a selection mechanism resolvin...
Tony J. Prescott, Fernando M. Montes Gonzál...
170views more  HEURISTICS 2008»
13 years 6 months ago
Accelerating autonomous learning by using heuristic selection of actions
This paper investigates how to make improved action selection for online policy learning in robotic scenarios using reinforcement learning (RL) algorithms. Since finding control po...
Reinaldo A. C. Bianchi, Carlos H. C. Ribeiro, Anna...
13 years 7 months ago
Action Selection for Single- and Multi-Robot Tasks Using Cooperative Extended Kohonen Maps
This paper presents an action selection framework based on an assemblage of self-organizing neural networks called Cooperative Extended Kohonen Maps. This framework encapsulates t...
Kian Hsiang Low, Wee Kheng Leow, Marcelo H. Ang Jr...
13 years 7 months ago
An Action Selection Architecture for an Emotional Agent
An architecture for action selection is presented linking emotion, cognition and behavior. It defines the information and emotion processes of an agent. The architecture has been...
Gertjan J. Burghouts, Dirk Heylen, Mannes Poel, Ri...
13 years 7 months ago
Action Selection in Bayesian Reinforcement Learning
My research attempts to address on-line action selection in reinforcement learning from a Bayesian perspective. The idea is to develop more effective action selection techniques b...
Tao Wang
13 years 8 months ago
Multi-robot Markov random fields
We propose Markov random fields (MRFs) as a probabilistic mathematical model for unifying approaches to multi-robot coordination or, more specifically, distributed action selectio...
Jesse Butterfield, Odest Chadwicke Jenkins, Brian ...
13 years 10 months ago
Knowledge Granularity and Action Selection
Abstract. In this paper we introduce the concept of knowledge granularity and study its influence on an agent's action selection process. Action selection is critical to an ag...
Yiming Ye, John K. Tsotsos