17 search results - page 2 / 4 » Binary action search for learning continuous-action control ... |
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...
AI
1999
Springer
13 years 4 months ago
1999
Springer
There are many different approaches to solving planning problems, one of which is the use of domain specific control knowledge to help guide a domain independent search algorithm. ...
ICRA
2005
IEEE
13 years 10 months ago
2005
IEEE
— We present a semi-parametric control policy representation and use it to solve a series of nonholonomic control problems with input state spaces of up to 7 dimensions. A neares...
CCIA
2005
Springer
13 years 10 months ago
2005
Springer
— This paper proposes a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, whe...
AAAI
2000
13 years 5 months ago
2000
Reinforcement learning (RL) can be impractical for many high dimensional problems because of the computational cost of doing stochastic search in large state spaces. We propose a ...