124 citations · 142 across the 5 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2023★ 1 cited
On The Fragility of Learned Reward Functions
Lev McKinney, Yawen Duan, David Krueger +1
Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer reward functions from human feedback and…
cs.LG2022★ 10 cited
Adversarial Policies Beat Superhuman Go AIs
Tony T. Wang, Adam Gleave, Tom Tseng +8
We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies against it, achieving a >97% win rate against KataGo running at superhuman settings. Our…
cs.LG2020★ 3 cited
CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search
Xin Chen, Yawen Duan, Zewei Chen +5
Neural Architecture Search (NAS) achieved many breakthroughs in recent years. In spite of its remarkable progress, many algorithms are restricted to particular search spaces. They…