Sciweavers

5075 search results - page 163 / 1015
» Convergence
Sort
View
NIPS
1998
15 years 5 months ago
Gradient Descent for General Reinforcement Learning
A simple learning rule is derived, the VAPS algorithm, which can be instantiated to generate a wide range of new reinforcementlearning algorithms. These algorithms solve a number ...
Leemon C. Baird III, Andrew W. Moore
ATAL
2010
Springer
15 years 5 months ago
Joint process games: from ratings to wikis
We introduce a game setting called a joint process, where the history of actions determine the state, and the state and agent properties determine the payoff. This setting is a sp...
Michael Munie, Yoav Shoham
MM
2010
ACM
123views Multimedia» more  MM 2010»
15 years 4 months ago
Coming together: negotiated content by multi-agents
In this paper, we describe a software system that generates unique musical compositions in realtime, created by four autonomous multi-agents. Given no explicit musical data, agent...
Arne Eigenfeldt
MM
2010
ACM
137views Multimedia» more  MM 2010»
15 years 4 months ago
Coming together: composition by negotiation
In this paper, we describe a software system that generates unique musical compositions in realtime, created by four autonomous multi-agents. Given no explicit musical data, agent...
Arne Eigenfeldt
CORR
2010
Springer
188views Education» more  CORR 2010»
15 years 4 months ago
A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers
High-dimensional statistical inference deals with models in which the the number of parameters p is comparable to or larger than the sample size n. Since it is usually impossible ...
Sahand Negahban, Pradeep Ravikumar, Martin J. Wain...