46 search results - page 1 / 10 » Discretization of Continuous Action Spaces in Extensive-Form... |
FLAIRS
2008
13 years 6 months ago
2008
Although several researchers have integrated methods for reinforcement learning (RL) with case-based reasoning (CBR) to model continuous action spaces, existing integrations typic...
ECML
2006
Springer
13 years 8 months ago
2006
Springer
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...
ACSC
2007
IEEE
13 years 10 months ago
2007
IEEE
As computer controlled entities are set to move and explore more complex environments they need to be able to perform navigation tasks, like finding minimal cost routes. Much wor...
ICMLA
2004
13 years 5 months ago
2004
We present JoSTLe, an algorithm that performs value iteration on control problems with continuous actions, allowing this useful reinforcement learning technique to be applied to p...
AUSAI
1999
Springer
13 years 8 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...