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 ...