Download PDFOpen PDF in browser

Object-sensitive Deep Reinforcement Learning

16 pagesPublished: October 19, 2017

Abstract

Deep reinforcement learning has become popular over recent years, showing superiority on different visual-input tasks such as playing Atari games and robot navigation. Although objects are important image elements, few work considers enhancing deep reinforcement learning with object characteristics. In this paper, we propose a novel method that can incorporate object recognition processing to deep reinforcement learning models. This approach can be adapted to any existing deep reinforcement learning frameworks. State-of-the-art results are shown in experiments on Atari games. We also propose a new approach called “object saliency maps” to visually explain the actions made by deep reinforcement learning agents.

Keyphrases: deep reinforcement learning, explainable model, object recognition, saliency map

In: Christoph Benzmüller, Christine Lisetti and Martin Theobald (editors). GCAI 2017. 3rd Global Conference on Artificial Intelligence, vol 50, pages 20-35.

BibTeX entry
@inproceedings{GCAI2017:Object_sensitive_Deep_Reinforcement,
  author    = {Yuezhang Li and Katia Sycara and Rahul Iyer},
  title     = {Object-sensitive Deep Reinforcement Learning},
  booktitle = {GCAI 2017. 3rd Global Conference on Artificial Intelligence},
  editor    = {Christoph Benzmüller and Christine Lisetti and Martin Theobald},
  series    = {EPiC Series in Computing},
  volume    = {50},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/h9zx},
  doi       = {10.29007/xtgm},
  pages     = {20-35},
  year      = {2017}}
Download PDFOpen PDF in browser