Rohin Shah
11 papers
· 2019–2025
· 4 conferences
· across top CS/AI conferences
Achievements
π£
Hot Topic Early Bird
π§
Keyword Pioneer
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(19)
π
Conference Polyglot
(4)
π
Academic Marathon
(6)
π
Cross-Pollinator
(4)
π
Renaissance Researcher
(5)
π
Triple Crown
π
Century Club
(11)
Conferences
NIPS (6)
ICLR (2)
ICML (2)
EMNLP (1)
Top co-authors
Keywords
reinforcement learning
(3)
ai safety
(2)
multi-agent system
(2)
imitation learning
(2)
sparse autoencoder
(2)
model analysis
(1)
reward function
(1)
neural network interpretability
(1)
markov decision process
(1)
behavior cloning
(1)
model evaluation
(1)
distribution shift
(1)
optimal policy
(1)
reward learning
(1)
latent representation
(1)
pairwise comparison
(1)
human feedback
(1)
benchmark dataset
(1)
language model
(1)
inverse reinforcement learning
(1)
Papers
Optimal Policies Tend To Seek Power
NIPS 2021