Search Results for author: Ahmed Hefny

Found 9 papers, 2 papers with code

Recurrent Predictive State Policy Networks

2 code implementations ICML 2018 Ahmed Hefny, Zita Marinho, Wen Sun, Siddhartha Srinivasa, Geoffrey Gordon

Predictive state policy networks consist of a recursive filter, which keeps track of a belief about the state of the environment, and a reactive policy that directly maps beliefs to actions, to maximize the cumulative reward.

OpenAI Gym

Predictive State Recurrent Neural Networks

no code implementations NeurIPS 2017 Carlton Downey, Ahmed Hefny, Boyue Li, Byron Boots, Geoffrey Gordon

We present a new model, Predictive State Recurrent Neural Networks (PSRNNs), for filtering and prediction in dynamical systems.

Tensor Decomposition

Practical Learning of Predictive State Representations

no code implementations14 Feb 2017 Carlton Downey, Ahmed Hefny, Geoffrey Gordon

Unfortunately it is not obvious how to apply apply an EM style algorithm in the context of PSRs as the Log Likelihood is not well defined for all PSRs.

An Efficient, Expressive and Local Minima-free Method for Learning Controlled Dynamical Systems

1 code implementation12 Feb 2017 Ahmed Hefny, Carlton Downey, Geoffrey J. Gordon

We propose a framework for modeling and estimating the state of controlled dynamical systems, where an agent can affect the system through actions and receives partial observations.

Stochastic Variance Reduction for Nonconvex Optimization

no code implementations19 Mar 2016 Sashank J. Reddi, Ahmed Hefny, Suvrit Sra, Barnabas Poczos, Alex Smola

We study nonconvex finite-sum problems and analyze stochastic variance reduced gradient (SVRG) methods for them.

Supervised Learning for Dynamical System Learning

no code implementations NeurIPS 2015 Ahmed Hefny, Carlton Downey, Geoffrey Gordon

To address this problem, we present a new view of dynamical system learning: we show how to learn dynamical systems by solving a sequence of ordinary supervised learning problems, thereby allowing users to incorporate prior knowledge via standard techniques such as L1 regularization.

Large-scale randomized-coordinate descent methods with non-separable linear constraints

no code implementations9 Sep 2014 Sashank Reddi, Ahmed Hefny, Carlton Downey, Avinava Dubey, Suvrit Sra

We develop randomized (block) coordinate descent (CD) methods for linearly constrained convex optimization.

Cannot find the paper you are looking for? You can Submit a new open access paper.