DRIVE: Diversity-Driven RL Fine-Tuning for VLA Generalization
Overview
DRIVE enhances VLA generalization via diversity in successful behaviors, improving out-of-domain performance on multiple benchmarks and a physical platform. Results show gains of +9.2 points on a dual-arm AgileX PiPER-X platform. Latest: DRIVE improves OOD success from 64.1% to 73.3% on a physical platform, showing real-world applicability.,
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · OOD performance: 5.3 other · Basis not reported · Differing source assertions
“h temporal alignment, and derives a success-conditioned intrinsic reward from relative behavioral diversity. This design encourages broader coverage of feasible solutions without rewarding diverse failures or superficial timing differences. Across LIBERO-Plus, ManiSkill3, and RoboTwin 2.0, DRIVE improves the average out-of-domain (OOD) performance over vanilla RL fine-tuning by 5.3 points on $\pi_0$ and 2.0 points on”
Exact source · revision 1Source owner not reported
Reported quantity · OOD performance: 2 other · Basis not reported · Differing source assertions
“h temporal alignment, and derives a success-conditioned intrinsic reward from relative behavioral diversity. This design encourages broader coverage of feasible solutions without rewarding diverse failures or superficial timing differences. Across LIBERO-Plus, ManiSkill3, and RoboTwin 2.0, DRIVE improves the average out-of-domain (OOD) performance over vanilla RL fine-tuning by 5.3 points on $\pi_0$ and 2.0 points on”
Exact source · revision 1Source owner not reported
Reported quantity · OOD success: 9.2 other · Basis not reported
“$\pi_{0.5}$. On a dual-arm AgileX PiPER-X platform, DRIVE further increases average OOD success from 64.1% to 73.3% (+9.2 points), demonstrating gains that persist under physical deployment.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsMany Ways to Succeed: Diversity-Driven RL Fine-Tuning for VLA Generalization
This research proposes DRIVE, a reinforcement learning fine-tuning method for vision-language-action (VLA) systems that leverages successful-behavior diversity to enhance generalization. By grouping rollouts under matched task conditions, aligning trajectories temporally, and deriving an intrinsic reward from relative behavioral diversity, DRIVE improves out-of-domain performance across multiple benchmarks, including LIBERO-Plus, ManiSkill3, and RoboTwin 2.0, with significant gains on a dual-arm AgileX PiPER-X platform.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).