Sciweavers

74 search results - page 2 / 15
» Interactive Selection of Visual Features through Reinforceme...
Sort
View
AROBOTS
1998
111views more  AROBOTS 1998»
13 years 3 months ago
Emergence and Categorization of Coordinated Visual Behavior Through Embodied Interaction
This paper discusses the emergence of sensorimotor coordination for ESCHeR, a 4DOF redundant foveated robot-head, by interaction with its environment. A feedback-error-learning(FEL...
Luc Berthouze, Yasuo Kuniyoshi
PKDD
2009
Springer
152views Data Mining» more  PKDD 2009»
13 years 10 months ago
Feature Selection for Value Function Approximation Using Bayesian Model Selection
Abstract. Feature selection in reinforcement learning (RL), i.e. choosing basis functions such that useful approximations of the unkown value function can be obtained, is one of th...
Tobias Jung, Peter Stone
ROBOCUP
2007
Springer
153views Robotics» more  ROBOCUP 2007»
13 years 9 months ago
Model-Based Reinforcement Learning in a Complex Domain
Reinforcement learning is a paradigm under which an agent seeks to improve its policy by making learning updates based on the experiences it gathers through interaction with the en...
Shivaram Kalyanakrishnan, Peter Stone, Yaxin Liu
MM
2010
ACM
115views Multimedia» more  MM 2010»
13 years 2 months ago
Interactive learning of heterogeneous visual concepts with local features
In the context of computer-assisted plant identification we are facing challenging information retrieval problems because of the very high within-class variability and of the lim...
Wajih Ouertani, Michel Crucianu, Nozha Boujemaa
ECML
2006
Springer
13 years 7 months ago
Task-Driven Discretization of the Joint Space of Visual Percepts and Continuous Actions
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Sébastien Jodogne, Justus H. Piater