Contingency awareness is the recognition that some aspects of a future observation are under an agent’s control while others are solely determined by the environment. This paper explores the idea of contingency awareness in reinforcement learning using the platform of Atari 2600 games. We introduce a technique for accurately identifying contingent regions and describe how to exploit this knowle...

Deep reinforcement learning has been shown to be a powerful framework for learning policies from complex high-dimensional sensory inputs to actions in complex tasks, such as the Atari domain. In this paper, we explore output representation modeling in the form of temporal abstraction to improve convergence and reliability of deep reinforcement learning approaches. We concentrate on macro-action...

T H E U C I U N D E R G R A D U A T E R E S E A R C H J O U R N A L F a c u l t y M e n t o r

The refined empirical line (REL) approach was used to convert the Earth Observing 1 (EO-1) Advanced Land Imager (ALI) sensor digital number (dn) to surface spectral reflectance ( ). The dn-torelation was derived from a bright target of known reflectance in the image, and the modeled estimates of the image dn at . The mean absolute percent difference ( ) between retrieved from ALI using the REL ...

Pseudo-random number generation on the Atari 2600 was commonly accomplished using a Linear Feedback Shift Register (LFSR). One drawback was that the initial seed for the LFSR had to be hard-coded into the ROM. To overcome this constraint, programmers sampled from the LFSR once per frame, including title and end screens. Since a human player will have some random amount of delay between seeing t...

We train a number of neural networks to play games Bowling, Breakout and Seaquest using information stored in the memory of a video game console Atari 2600. We consider four models of neural networks which differ in size and architecture: two networks which use only information contained in the RAM and two mixed networks which use both information in the RAM and information from the screen. As ...

designing effective strategies for sediment management and control is closely related to identification of sediment sources in a drainage basin. one of the methods for investigating sediment sources is using magnetic tracers for erosion and sediment yield studies. sediment source identification using magnetic characteristics is a simple, inexpensive, quick and non-destructive method having appl...