Sciweavers

350 search results - page 45 / 70
» Approximation Algorithms for Unique Games
Sort
View
TSMC
2008
146views more  TSMC 2008»
13 years 7 months ago
Decentralized Learning in Markov Games
Learning Automata (LA) were recently shown to be valuable tools for designing Multi-Agent Reinforcement Learning algorithms. One of the principal contributions of LA theory is tha...
Peter Vrancx, Katja Verbeeck, Ann Nowé
TCOM
2010
133views more  TCOM 2010»
13 years 6 months ago
Transmission control in cognitive radio as a Markovian dynamic game: Structural result on randomized threshold policies
Abstract——This paper considers an uplink time division multiple access (TDMA) cognitive radio network where multiple cognitive radios (secondary users) attempt to access a spect...
J. Huang, V. Krishnamurthy
ATAL
2005
Springer
14 years 1 months ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson
ICPR
2002
IEEE
14 years 8 months ago
Fractional Component Analysis (FCA) for Mixed Signals
This paper proposes the fractional component analysis (FCA), whose goal is to decompose the observed signal into component signals and recover their fractions. The uniqueness of o...
Asanobu Kitamoto
ICALP
2004
Springer
14 years 28 days ago
The Power of Verification for One-Parameter Agents
We initiate the study of mechanisms with verification for one-parameter agents. We give an algorithmic characterization of such mechanisms and show that they are provably better ...
Vincenzo Auletta, Roberto De Prisco, Paolo Penna, ...