340 search results - page 39 / 68 » Kernelized value function approximation for reinforcement le... |
113
Voted
IJCAI
2007
15 years 3 months ago
2007
We introduce an approach to autonomously creating state space abstractions for an online reinforcement learning agent using a relational representation. Our approach uses a tree-b...
118
click to vote
ML
2002
ACM
15 years 2 months ago
2002
ACM
TD() is a popular family of algorithms for approximate policy evaluation in large MDPs. TD() works by incrementally updating the value function after each observed transition. It h...
107
click to vote
GECCO
2006
Springer
15 years 6 months ago
2006
Springer
Recently, studies with the XCS classifier system on Boolean functions have shown that in certain types of functions simple crossover operators can lead to disruption and, conseque...
128
Voted
COLT
2003
Springer
15 years 7 months ago
2003
Springer
Recent work has introduced Boolean kernels with which one can learn linear threshold functions over a feature space containing all conjunctions of length up to k (for any 1 ≤ k ...
116
click to vote
NIPS
2008
15 years 3 months ago
2008
We present a multi-label multiple kernel learning (MKL) formulation in which the data are embedded into a low-dimensional space directed by the instancelabel correlations encoded ...