Back to AI News
arxiv

DexDICE reconciles safety and performance in offline imitation learning

DexDICE introduces dual-expert offline imitation learning, using safety-compliant but potentially suboptimal demonstrations alongside high-return demonstrations that may violate safety guidelines. The method combines DICE-style offline learning with safe support constraints rather than conventional distribution constraints. The authors prove that the ideal constrained solution has zero unsafe-region visitation with high probability. They evaluate DexDICE on a re-curated DSRL benchmark and a real-world mobile-robot navigation task trained from human teleoperation, reporting improved performance and robustness to data scarcity and quality degradation.

AI Brief

It offers a concrete offline imitation learning method for balancing safety and performance when only separate safe and high-performing demonstrations are available.

arXiv:2611.09433v1 Announce Type: cross Abstract: Ensuring high returns while providing strong safety guarantees in offline imitation learning (IL) is a fundamental challenge: existing approaches either rely on explicitly specified cost functions, which are difficult to design for complex real-world safety constraints, or require expert demonstrations that are both safe and high-performing, which are often too costly to collect. We introduce dual-expert imitation learning, which leverages two complementary data sources: (i) safety-compliant demonstrations that faithfully follow safety guidelines but may be suboptimal, and (ii) performance-oriented demonstrations that achieve high returns but may violate safety guidelines. To address this problem, we propose DexDICE (Dual-expert offline imitation learning via stationary DIstribution Correction Estimation). Instead of conventional distribution constraints, DexDICE combines DICE-style offline learning with safe support constraints, enabling agents to exploit high-return behaviors while remaining within safety-compliant regions. We prove that the ideal solution satisfying this constraint exactly has zero unsafe-region visitation with high probability. We evaluate DexDICE on a re-curated DSRL benchmark and validate it on a real-world mobile-robot navigation task trained directly from human teleoperation demonstrations, where it substantially outperforms baselines and remains robust to data scarcity and quality degradation.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!