343 search results - page 13 / 69 » Action discovery for reinforcement learning |
ICRA
1995
IEEE
13 years 11 months ago
1995
IEEE
This paper presents a method of vision-based reinforcement learning by which a robot learns to shoot a ball into a goal, and discusses several issues in applying the reinforcement...
ICML
2005
IEEE
14 years 8 months ago
2005
IEEE
We present a new subgoal-based method for automatically creating useful skills in reinforcement learning. Our method identifies subgoals by partitioning local state transition gra...
AAAI
1996
13 years 9 months ago
1996
Procedural representations of control policies have two advantages when facing the scale-up problem in learning tasks. First they are implicit, with potential for inductive genera...
ICML
2004
IEEE
14 years 8 months ago
2004
IEEE
Motivated by the interest in relational reinforcement learning, we introduce a novel relational Bellman update operator called ReBel. It employs a constraint logic programming lan...
IAT
2007
IEEE
14 years 2 months ago
2007
IEEE
This paper proposes a mechanism of noise tolerance for reinforcement learning algorithms. An adaptive agent that employs reinforcement learning algorithms may receive and accumula...