Simple nearest-neighbor and segment-matching reward functions match or beat Optimal Transport based Inverse RL across 32 benchmarks.
Eventually, their total scores match each other
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Is Optimal Transport Necessary for Inverse Reinforcement Learning?
Simple nearest-neighbor and segment-matching reward functions match or beat Optimal Transport based Inverse RL across 32 benchmarks.