Standard inverse reinforcement learning models identify rewards only up to reward shaping and redistribution, and are not robust to even small misspecifications of transition dynamics or discount factors.
To show that f is P -robust to misspecification with g, we must show that the following two conditions hold:
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Partial Identifiability and Misspecification in Inverse Reinforcement Learning
Standard inverse reinforcement learning models identify rewards only up to reward shaping and redistribution, and are not robust to even small misspecifications of transition dynamics or discount factors.