Sciweavers

267 search results - page 40 / 54
» Distribution arithmetic for stochastical analysis
Sort
View
IJCAI
2003
13 years 10 months ago
Covariant Policy Search
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
J. Andrew Bagnell, Jeff G. Schneider
CORR
2008
Springer
114views Education» more  CORR 2008»
13 years 8 months ago
Network-based consensus averaging with general noisy channels
This paper focuses on the consensus averaging problem on graphs under general noisy channels. We study a particular class of distributed consensus algorithms based on damped updat...
Ram Rajagopal, Martin J. Wainwright
CDC
2010
IEEE
118views Control Systems» more  CDC 2010»
13 years 3 months ago
Sufficient conditions for stabilizability over Gaussian relay and cascade channels
We present sufficient conditions for stabilizability of an unstable linear time invariant scalar system across an additive white Gaussian noise channel, with a relay assisting the ...
Utsaw Kumar, Vijay Gupta, J. Nicholas Laneman
COCOON
2008
Springer
13 years 10 months ago
Average-Case Competitive Analyses for One-Way Trading
Consider a trader who exchanges one dollar into yen and assume that the exchange rate fluctuates within the interval [m, M]. The game ends without advance notice, then the trader ...
Hiroshi Fujiwara, Kazuo Iwama, Yoshiyuki Sekiguchi
PODC
2006
ACM
14 years 2 months ago
Computing separable functions via gossip
Motivated by applications to sensor, peer-to-peer, and adhoc networks, we study the problem of computing functions of values at the nodes in a network in a totally distributed man...
Damon Mosk-Aoyama, Devavrat Shah