Search
Skip to Search Results- 4Dynamic Programming
- 1Automated Planning and Scheduling
- 1Cognitive Radio Networks
- 1Convolutional Neural Networks
- 1Differentiable Programming
- 1Domain Independent Artificial Intelligence Planning
-
Extending Differentiable Programming to include Non-differentiable Modules using Differentiable Bypass for Combining Convolutional Neural Networks and Dynamic Programming into an End-to-end Trainable Framework
DownloadSpring 2019
Differentiable Programming is the paradigm where different functions or modules are combined into a unified pipeline with the purpose of applying end-to-end learning or optimization. A natural impediment is the non-differentiability characteristic of many modules. This thesis proposes a new way...
-
Fall 2015
We study a channel selection problem in cognitive radio with imperfect spectrum sensing. In this problem, a secondary (unlicensed) user must select a subset of M channels out of N channels to sense. The user then accesses up to K ≤ M channels that were sensed free. The objective is to maximize...
-
Spring 2013
Cost overrun and schedule slippage are common problems for mega industrial construction projects. Lack of effective planning and scheduling tools is identified as a major contributing factor to poor project performance. Planning and scheduling tools should be custom designed to address the...
-
2006
Wang, Tao, Schuurmans, Dale, Bowling, Michael
Technical report TR06-26. We investigate the dual approach to dynamic programming and reinforcement learning, based on maintaining an explicit representation of stationary distributions as opposed to value functions. A significant advantage of the dual approach is that it allows one to exploit...