← Back to all news
arXiv Machine Learning By Songyuan Zhang, Baljeet Singh, Sarthak Ranjeet Kaingade, Chuchu Fan, Bryan Trinh

FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems

Read the original on arXiv Machine Learning →

FAITH is a model‑free reinforcement learning framework that separates safety from task performance by using a learned safety filter. The filter approximates the optimal state‑action safety value with a feedforward network, allowing the task policy to optimize return through filtered dynamics without a competing safety term. Experiments on a double integrator, Safety Gym, a 29‑DoF humanoid, and a real Unitree G1 show that FAITH achieves high returns while maintaining near‑perfect safety and handling infeasible starts gracefully.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 21

Provably Optimal Reinforcement Learning under Safety Filtering

The paper proves that using a permissive safety filter in reinforcement learning does not compromise asymptotic performance. By formalizing safety through a safety‑critical Markov decision process and a filtered MDP, the authors show that optimal policies in the filtered MDP achieve the same return as the best safe policy in the original setting. Experiments on Safety Gymnasium confirm zero violations during training and performance that matches or exceeds unfiltered baselines.

By Donggeon David Oh, Duy P. Nguyen, Haimin Hu, Jaime Fern\'andez Fisac
reinforcement-learningsafety
More like this →
arXiv Machine Learning
Sep 3

Humanoid Safe Stop via Learned Stoppability Value

The paper introduces Safe-Stop, a task‑agnostic framework for humanoid robots that determines whether an emergency stop command can be safely executed from the current state. It couples a learned stop policy with two complementary stoppability estimators: a stop‑probability estimator trained on outcomes of a fixed stop policy, and a reach‑avoidance estimator trained via Hamilton‑Jacobi backup. By requiring agreement between both estimators before committing to a stop, Safe‑Stop can robustly decide to stop or hand off to a fall‑damping fallback without needing retraining for different upstream tasks.

By Junfeng Long, Pieter Abbeel, Koushil Sreenath, Roberto Horowitz, Guanya Shi, C. Karen Liu
robotics
More like this →
arXiv AI
Sep 12

ActSafeGuard: Differentiable and Training-Aligned Constraint Enforcement for Flow-Matching Policies

arXiv:2609. 11697v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) and World-Action Models (WAMs) have demonstrated strong capabilities in general-purpose robotic manipulation, yet their generated actions may violate hard physical constraints and therefore be unsafe or infeasible for deployment.

By Jianming Ma, Rongjun Jin, Xiaxi Si, Yang Zhang, Yiheng Li, Yue Gao
roboticsmultimodalsafety
More like this →