影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
54.22/100
前 6.7%
全站排名 #4,324
发表论文7 篇
平均评分
年均产出3.5 篇/年
Joar Max Viktor Skalse
研究方向
decision theory · reinforcement learning · inverse reinforcement learning · reward learning · symbolic AI · learning theory
14
On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning
ICLR 2024Poster
通讯16
Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
ICLR 2024Poster
一作17
STARC: A General Framework For Quantifying Differences Between Reward Functions
ICLR 2024Poster
一作14
Goodhart's Law in Reinforcement Learning
ICLR 2024Poster
通讯10
Characterising Partial Identifiability in Inverse Reinforcement Learning For Agents With Non-Exponential Discounting
ICLR 2024Rejected
一作