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

arXiv: https://arxiv.org/abs/2610.12432 · HTML: https://mlsanity.com/paper/2610.12432/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 13 of its 42 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- Deep reinforcement learning methods / [Safe and constrained RL](https://mlsanity.com/deeprl/safe-and-constrained-rl/)

## Builds on (most cited first, 13 of 13)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning](https://mlsanity.com/paper/2511.04831/) (2025)
- [CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions](https://mlsanity.com/paper/2510.14959/) (2025)
- [SafeFall: Learning Protective Control for Humanoid Robots](https://mlsanity.com/paper/2511.18509/) (2025)
- [Synthesis and Deployment of Maximal Robust Control Barrier Functions through Adversarial Reinforcement Learning](https://mlsanity.com/paper/2604.13192/) (2026)
- [Unified Humanoid Fall-Safety Policy from a Few Demonstrations](https://mlsanity.com/paper/2511.07407/) (2025)
- [Dexterous Safe Control for Humanoids in Cluttered Environments via Projected Safe Set Algorithm](https://mlsanity.com/paper/2502.02858/) (2025)
- [PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball](https://mlsanity.com/paper/2607.28623/) (2026)
- [Deep QP Safety Filter: Model-free Learning for Reachability-based Safety Filter](https://mlsanity.com/paper/2601.21297/) (2026)
- [Provably Safe, Yet Scalable Reinforcement Learning](https://mlsanity.com/paper/2606.14536/) (2026)
- [λ-Reachability: Geometric-Horizon Safety Bellman Equations for Humanoid Safety](https://mlsanity.com/paper/2606.16022/) (2026)
- [Safe Execution of RL Policies Via Acceleration-Based CBF-QP Constraint Enforcement for Real-World Robotic Deployments](https://mlsanity.com/paper/2607.14488/) (2026)

## Abstract (arXiv)

Safe reinforcement learning commonly places safety and task performance in the same policy objective, where they can introduce competing updates. Safety filters separate them at action execution, but classical designs require an analytic safety function and dynamics model, and standard minimal-intervention filters are myopic to long-horizon task return because they minimize only instantaneous action deviation. Hard projections are also undefined when no safe action exists. We present FAITH, a feasibility-aware, model-free framework that approximates the optimal state-action safety value and amortizes minimal-intervention filtering with a feedforward network. The task policy optimizes the task return through the filtered dynamics, which recovers the feasible constrained problem without a competing safety term in the task-policy update. When no action satisfies the learned safety condition, the same filter approaches the action with minimum predicted peak harm. On a double integrator example and a Safety Gym environment, FAITH achieves the highest return among methods with no feasible-start violations and matches the lowest harm from infeasible starts. On a 29-DoF humanoid, it reaches a 99.95% safety rate while retaining 97% of the unfiltered return in Walking-Avoid, and obtains the highest measured safety rate in Push-Avoid by learning to sacrifice balancing and fall away from the protected region. The same policies are also demonstrated on a real-world Unitree G1 humanoid.