Selecting 50% of robot demonstrations by maximizing exposure to reusable primitive-transition patterns outperforms full-data training while halving training steps.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
TRIRL uses a trust-region insight to allow explicit dual ascent in IRL with local policy searches, claiming monotonic improvement and better generalization than prior methods.
citing papers explorer
-
SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models
Selecting 50% of robot demonstrations by maximizing exposure to reusable primitive-transition patterns outperforms full-data training while halving training steps.
-
Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
TRIRL uses a trust-region insight to allow explicit dual ascent in IRL with local policy searches, claiming monotonic improvement and better generalization than prior methods.