SOURCE-LINKED INTELLIGENCE
REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff
A central goal of autonomous reinforcement learning is continuous policy training without external resets. However, existing paradigms largely depend on underlying environmental reversibility, a property absent in real world manipulation, where events such as pushing objects off tables or spilling granular substances cannot be undone. We introduce REVERSAL-BENCH, a benchmark that controls reversibility via a continuous parameter $ρ\in [0, 1]$ and provides a reset oracle, a ground-truth verification mechanism to test state recoverability across eight manipulation settings in five physics engine
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-15T18:57:24.000Z
First collected: 2026-09-20T08:20:57.646Z. This is not the publication date.