Attention Guided Imitation Learning and Reinforcement Learning

AAAI 2019 pp. 9906-9907

doi:10.1609/AAAI.V33I01.33019906 /aaai/2019/zhang2019aaai-attention/

Abstract

We propose a framework that uses learned human visual attention model to guide the learning process of an imitation learning or reinforcement learning agent. We have collected high-quality human action and eye-tracking data while playing Atari games in a carefully controlled experimental setting. We have shown that incorporating a learned human gaze model into deep imitation learning yields promising results.

PDF AAAI Semantic Scholar

Cite

Text

Zhang. "Attention Guided Imitation Learning and Reinforcement Learning." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33019906

Markdown

[Zhang. "Attention Guided Imitation Learning and Reinforcement Learning." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/zhang2019aaai-attention/) doi:10.1609/AAAI.V33I01.33019906

BibTeX

@inproceedings{zhang2019aaai-attention,
  title     = {{Attention Guided Imitation Learning and Reinforcement Learning}},
  author    = {Zhang, Ruohan},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {9906-9907},
  doi       = {10.1609/AAAI.V33I01.33019906},
  url       = {https://mlanthology.org/aaai/2019/zhang2019aaai-attention/}
}