Share Email Print

Proceedings Paper

Learning optimal actions with imperfect images
Author(s): Song Jun Park; Dale R. Shires
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Deep reinforcement learning has been successful in training an agent to play at human-level in Atari games. Here, outputs of the game images were fed into a deep neural network to compute optimal actions. Conceptually, reinforcement learning can be viewed as the intersection of planning, uncertainty, and learning. In this paper, deep reinforcement learning method is applied to solve a problem formulated as a partially observable Markov decision process (POMDP). Specifically, the input images are perturbed to introduce imperfect knowledge. POMDP formulations assume uncertainties in the true state space and thus a more accurate representation of the real-world scenarios. The deep Q-network is adopted to see if an optimal sequence of actions can be learned when the inputs are not fully observable. Experimental results indicated that optimal strategies were discovered by deep reinforcement learning in majority of test cases, albeit slower to converge to the optimal solution.

Paper Details

Date Published: 4 June 2019
PDF: 7 pages
Proc. SPIE 10996, Real-Time Image Processing and Deep Learning 2019, 109960F (4 June 2019); doi: 10.1117/12.2518921
Show Author Affiliations
Song Jun Park, U.S. Army Research Lab. (United States)
Dale R. Shires, U.S. Army Research Lab. (United States)

Published in SPIE Proceedings Vol. 10996:
Real-Time Image Processing and Deep Learning 2019
Nasser Kehtarnavaz; Matthias F. Carlsohn, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?