360 search results - page 3 / 72 » Combining Learned Discrete and Continuous Action Models |
APSEC
2002
IEEE
14 years 3 months ago
2002
IEEE
Continuous action systems (CAS) is a formalism intended for modeling hybrid systems (systems that combine discrete control with continuous behavior), and proving properties about ...
ICRA
2009
IEEE
14 years 5 months ago
2009
IEEE
Abstract— Continuous action sets are used in many reinforcement learning (RL) applications in robot control since the control input is continuous. However, discrete action sets a...
AUSAI
1999
Springer
14 years 3 months ago
1999
Springer
Abstract. Q-learning can be used to learn a control policy that maximises a scalar reward through interaction with the environment. Qlearning is commonly applied to problems with d...
ICFEM
2009
Springer
14 years 5 months ago
2009
Springer
An extension to action systems is presented facilitating the modeling of continuous behavior in the discrete domain. The original action system formalism has been developed by Back...
AAMAS
2007
Springer
14 years 5 months ago
2007
Springer
Abstract. Reinforcement learning (RL) is a widely used learning paradigm for adaptive agents. There exist several convergent and consistent RL algorithms which have been intensivel...