1234 search results - page 203 / 247 » Multi-criteria Reinforcement Learning |
IROS
2006
IEEE
14 years 3 months ago
2006
IEEE
— This paper presents a hybrid control architecture for autonomous robotic fishes which are able to swim and navigate in unknown or dynamically changing environments. It has a t...
CEEMAS
2005
Springer
14 years 2 months ago
2005
Springer
We show that reputation is a basic ingredient in the Virtual Organisation (VO) formation process. Agents can use their experiences gained in direct past interactions to model other...
ICRA
1994
IEEE
14 years 1 months ago
1994
IEEE
There is a close relationship between harmonic functions { which have recently been proposed for path planning { and hitting probabilities for random processes. The hitting probab...
ROBOCUP
2000
Springer
14 years 19 days ago
2000
Springer
Q-learning, a most widely used reinforcement learning method, normally needs well-defined quantized state and action spaces to converge. This makes it difficult to be applied to re...
ESANN
2008
13 years 10 months ago
2008
The aim of this paper is to enhance the performance of a reinforcement learning game agent controller, within a dynamic game environment, through the retention of learned informati...