Center for Human-Compatible AI Retweeted Adam Gleave
Adam Gleave (CHAI Researcher) has published his paper on adversarial policies! Check it out! He also wrote a blog post about it on the BAIR blog.https://twitter.com/ARGleave/status/1243373829650395138 …
Center for Human-Compatible AI added,
1:53
Adam Gleave @ARGleave
Excited to share our work @iclr_conf: deep RL policies can be attacked by another agent taking actions that create natural adversarial observations. (1/5)
Blog: http://bair.berkeley.edu/blog/2020/03/27/attacks/ …
Paper: http://openreview.net/forum?id=HJgEMpVFwB …
Videos: http://adversarialpolicies.github.io/
Code: http://github.com/humancompatibleai/adversarial-policies … pic.twitter.com/103sB0MXGe
Show this thread
9:01 PM - 26 Mar 2020
0 replies
0 retweets
4 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.