Sciweavers

236 search results - page 35 / 48
» Non-linear dynamics in multiagent reinforcement learning alg...
Sort
View
SIGDIAL
2010
13 years 5 months ago
Sparse Approximate Dynamic Programming for Dialog Management
Spoken dialogue management strategy optimization by means of Reinforcement Learning (RL) is now part of the state of the art. Yet, there is still a clear mismatch between the comp...
Senthilkumar Chandramohan, Matthieu Geist, Olivier...
JMLR
2008
92views more  JMLR 2008»
13 years 7 months ago
Theoretical Advantages of Lenient Learners: An Evolutionary Game Theoretic Perspective
This paper presents the dynamics of multiple learning agents from an evolutionary game theoretic perspective. We provide replicator dynamics models for cooperative coevolutionary ...
Liviu Panait, Karl Tuyls, Sean Luke
NIPS
1993
13 years 9 months ago
Convergence of Stochastic Iterative Dynamic Programming Algorithms
Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms,includ...
Tommi Jaakkola, Michael I. Jordan, Satinder P. Sin...
ADHOCNETS
2010
Springer
13 years 4 months ago
DCLA: A Duty-Cycle Learning Algorithm for IEEE 802.15.4 Beacon-Enabled WSNs
The current specification for IEEE 802.15.4 beacon-enabled networks does not define how active and sleep schedules should be configured in order to achieve the optimal network perf...
Rodolfo de Paz Alberola, Dirk Pesch
JCP
2007
143views more  JCP 2007»
13 years 7 months ago
Noisy K Best-Paths for Approximate Dynamic Programming with Application to Portfolio Optimization
Abstract— We describe a general method to transform a non-Markovian sequential decision problem into a supervised learning problem using a K-bestpaths algorithm. We consider an a...
Nicolas Chapados, Yoshua Bengio