Sciweavers

NIPS
1993
13 years 6 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...
NIPS
1993
13 years 6 months ago
Mixtures of Controllers for Jump Linear and Non-Linear Plants
We describe an extension to the Mixture of Experts architecture for modelling and controlling dynamical systems which exhibit multiple modesof behavior. This extension is based on...
Timothy W. Cacciatore, Steven J. Nowlan
NIPS
1993
13 years 6 months ago
Surface Learning with Applications to Lipreading
Most connectionist research has focused on learning mappings from one space to another (eg. classification and regression). This paper introduces the more general task of learnin...
Christoph Bregler, Stephen M. Omohundro
NIPS
1993
13 years 6 months ago
Packet Routing in Dynamically Changing Networks: A Reinforcement Learning Approach
This paper describes the Q-routing algorithm for packet routing, in which a reinforcement learning module is embedded into each node of a switching network. Only local communicati...
Justin A. Boyan, Michael L. Littman
NIPS
1993
13 years 6 months ago
Credit Assignment through Time: Alternatives to Backpropagation
Learning to recognize or predict sequences using long-term context has many applications. However, practical and theoretical problems are found in training recurrent neural networ...
Yoshua Bengio, Paolo Frasconi
NIPS
1993
13 years 6 months ago
Using Local Trajectory Optimizers to Speed Up Global Optimization in Dynamic Programming
Dynamic programming provides a methodology to develop planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have ...
Christopher G. Atkeson
NIPS
1997
13 years 6 months ago
Graph Matching with Hierarchical Discrete Relaxation
Our aim in this paper is to develop a Bayesian framework for matching hierarchical relational models. Such models are widespread in computer vision. The framework that we adopt fo...
Richard C. Wilson, Edwin R. Hancock