509 search results - page 12 / 102 » Compositional Models for Reinforcement Learning |
FUZZIEEE
2007
IEEE
14 years 2 months ago
2007
IEEE
— Reinforcement learning (RL) is a learning control paradigm that provides well-understood algorithms with good convergence and consistency properties. Unfortunately, these algor...
IROS
2009
IEEE
14 years 2 months ago
2009
IEEE
— Partially Observable Markov Decision Processes (POMDPs) provide a rich mathematical model to handle realworld sequential decision processes but require a known model to be solv...
ICML
2008
IEEE
14 years 8 months ago
2008
IEEE
We show that linear value-function approximation is equivalent to a form of linear model approximation. We then derive a relationship between the model-approximation error and the...
NIPS
2007
13 years 9 months ago
2007
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a mo...
NIPS
2003
13 years 9 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...