Entropy-regularized Min-Max-IRL achieves O(n^{-1}) rates for trajectory-level KL divergence and squared parameter error in the Hessian norm under misspecification in Borel MDPs.
To this end, we construct an example wheref(r+r′ 2 )>max{f(r),f(r′)}
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fast Rates for Inverse Reinforcement Learning
Entropy-regularized Min-Max-IRL achieves O(n^{-1}) rates for trajectory-level KL divergence and squared parameter error in the Hessian norm under misspecification in Borel MDPs.