1166 search results - page 118 / 234 » Negotiating Using Rewards |
81
Voted
TNN
2008
15 years 2 months ago
2008
An experimental study on two decision issues for wrapper feature selection (FS) with multilayer perceptrons and the sequential backward selection (SBS) procedure is presented. The ...
113
click to vote
GLOBECOM
2010
IEEE
15 years 10 days ago
2010
IEEE
The existing credit-based mechanisms mainly focus on stimulating the rational packet droppers to relay other nodes' packets, but they cannot identify the irrational packet dro...
128
Voted
ICMLA
2010
15 years 9 days ago
2010
Abstract-- Policy Gradients with Parameter-based Exploration (PGPE) is a novel model-free reinforcement learning method that alleviates the problem of high-variance gradient estima...
171
click to vote
SGAI
2010
Springer
15 years 6 days ago
2010
Springer
This paper presents work on using hierarchical long term memory to reduce the memory requirements of nearest sequence memory (NSM) learning, a previously published, instance-based ...
166
Voted
NFM
2011
14 years 9 months ago
2011
Abstract. In parametric Markov Decision Processes (PMDPs), transition probabilities are not fixed, but are given as functions over a set of parameters. A PMDP denotes a family of ...