827 search results - page 26 / 166 » Variational methods for Reinforcement Learning |
SBIA
2004
Springer
15 years 5 months ago
2004
Springer
This work presents a new algorithm, called Heuristically Accelerated Q–Learning (HAQL), that allows the use of heuristics to speed up the well-known Reinforcement Learning algori...
95
Voted
ICONIP
2004
15 years 1 months ago
2004
Variational methods have proved popular and effective for inference and learning in intractable graphical models. An attractive feature of the approaches based on the Kullback-Lei...
98
Voted
IJCAI
2003
15 years 1 months ago
2003
We present a new algorithm, GM-Sarsa(0), for finding approximate solutions to multiple-goal reinforcement learning problems that are modeled as composite Markov decision processe...
113
click to vote
NIPS
2003
15 years 1 months ago
2003
We exploit some useful properties of Gaussian process (GP) regression models for reinforcement learning in continuous state spaces and discrete time. We demonstrate how the GP mod...
76
Voted
FLAIRS
1998
15 years 1 months ago
1998
Manyindustrial processes involve makingparts with an assemblyof machines, where each machinecarries out an operation on a part, and the finished product requires a wholeseries of ...