340 search results - page 29 / 68 » Kernelized value function approximation for reinforcement le... |
133
click to vote
ICML
2006
IEEE
16 years 3 months ago
2006
IEEE
Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms co...
130
click to vote
GECCO
2010
Springer
15 years 5 months ago
2010
Springer
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
106
Voted
NIPS
2008
15 years 3 months ago
2008
Many interesting problems, including Bayesian network structure-search, can be cast in terms of finding the optimum value of a function over the space of graphs. However, this fun...
120
Voted
ICML
2005
IEEE
16 years 3 months ago
2005
IEEE
In this paper we consider sampling based fitted value iteration for discounted, large (possibly infinite) state space, finite action Markovian Decision Problems where only a gener...
126
Voted
NIPS
2008
15 years 3 months ago
2008
In kernel-based regression learning, optimizing each kernel individually is useful when the data density, curvature of regression surfaces (or decision boundaries) or magnitude of...