Reward Identification in Inverse Reinforcement Learning
Kuno Kim 1 Kirankumar Shiragur 1 Shivam Garg 1 Stefano Ermon 1
Abstract MDPs to build computational models (Niv, 2009) of real-
world, rational decision makers such as investors (Dixit
We study the problem of reward identifiability
et al., 1994; Rust, 1994), farmers (Nielsen and Kristensen,
in the context of Inverse Re ...


雷达卡




京公网安备 11010802022788号







