Joar Skalse
6 papers
· 2021–2023
· 5 conferences
· across top CS/AI conferences
Achievements
π
Interdisciplinary Bridge
π
Conference Polyglot
(5)
π
Renaissance Researcher
(5)
π
Cross-Pollinator
(15)
πΊοΈ
Taxonomy Completionist
(18)
π§
Keyword Pioneer
β
The Questioner
Conferences
NIPS (2)
AAAI (1)
IJCAI (1)
JMLR (1)
UAI (1)
Top co-authors
Keywords
reward function
(3)
multi-objective reinforcement learning
(2)
reinforcement learning
(2)
decision theory
(1)
preference learning
(1)
inverse reinforcement learning
(1)
action-value function
(1)
bayesian posterior
(1)
deep neural network
(1)
reward hacking
(1)
safety constraint
(1)
deterministic policy
(1)
reward function learning
(1)
lexicographic optimization
(1)
risk-sensitive reinforcement learning
(1)
value-based method
(1)
stochastic policy
(1)
overparameterized regime
(1)
value-based reinforcement learning
(1)
proxy reward
(1)
Papers
Is SGD a Bayesian sampler? Well, almost
JMLR 2021