Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs
Clicks: 69
ID: 283457
2021
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This
article has not been analysed, so there is no overall score —
reader engagement is measured and shown alongside.
Reader Engagement
Steady Performance
20.4
/100
69 views
20 readers
AI Quality Assessment
Not analyzed
Readership in this journal
SteadyRanked #419 of 803 articles by views in arXiv
Most read
Least read
Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 803 in total.
Mint this article as an NFT
Not yet mintedCreate a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.
5
SUSD
one-off · no wallet required
Abstract
The use of deep neural networks as function approximators has led to striking
progress for reinforcement learning algorithms and applications. Yet the
knowledge we have on decision boundary geometry and the loss landscape of
neural policies is still quite limited. In this paper we propose a framework to
investigate the decision boundary and loss landscape similarities across states
and across MDPs. We conduct experiments in various games from Arcade Learning
Environment, and discover that high sensitivity directions for neural policies
are correlated across MDPs. We argue that these high sensitivity directions
support the hypothesis that non-robust features are shared across training
environments of reinforcement learning agents. We believe our results reveal
fundamental properties of the environments used in deep reinforcement learning
training, and represent a tangible step towards building robust and reliable
deep reinforcement learning agents.
| Reference Key |
korkmaz2021deep
Use this key to autocite in the manuscript while using
SciMatic Manuscript Manager or Thesis Manager
|
|---|---|
| Authors | Ezgi Korkmaz |
| Journal | arXiv |
| Year | 2021 |
| DOI |
DOI not found
|
| URL | |
| Keywords |
Citations
No citations found. To add a citation, contact the admin at info@scimatic.org
Comments
No comments yet. Be the first to comment on this article.