mlsanityData to 14 Oct 2026

parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learning

arXiv 2605.15509 ↗First posted 15 May 2026cs.LG cs.ROcited by 0

On the map: Deep reinforcement learning methods → Safe and constrained RL

Abstract (arXiv)

While Isaac Lab provides massive parallel UAV simulation, OmniSafe and safe-control-gym provide constrained-RL benchmarks, and CBFKit provides control-barrier-function synthesis tooling, no existing framework unifies these capabilities for end-to-end safety-constrained training. ParallelCBF is the first framework to unify (i)~tensor-parallel UAV environments, (ii)~hard-gate CBF safety filters, (iii)~sharded BC-to-RL pipelines, and (iv)~first-class operational auditability -- pre-registration, watchdog registries, failure forensics, and dataset audits as composable APIs rather than user-implemented scripts. We release ParallelCBF v0.1.0 under Apache~2.0 with a four-layer composable API, a CPU PyTorch reference implementation of a dual-barrier (squared / linear-predictive) CBF, property-based safety invariance tests across vectorized batch sizes that complete in 1.67~s for the full 39-test suite, and a 31,415-episode behavior-cloning collection campaign whose curriculum mix, per-bucket yields, and dataset SHA-256 are auditable through the framework's own textttops primitives. We report a representative end-to-end pipeline execution in which the framework's auditability layer halted a downstream training stage that did not meet pre-registered convergence criteria, preventing silent propagation of a degraded checkpoint -- an architectural property we argue is necessary, not merely useful, for reproducible empirical robotics research. The framework is installable via textttpip install parallelcbf; source and release artifacts are available at https://github.com/xiaoyang-123-cell/ParallelCBF.

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 8 of its 13 references that are in the map. First posted on arXiv 15 May 2026.

Builds on

8 of 13 references.

References · 8

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Deep Reinforcement Learning that Matterscited by 754
  3. 2019Control Barrier Functions: Theory and Applicationscited by 372
  4. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 322
  5. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
  6. 2017OSQP: An Operator Splitting Solver for Quadratic Programscited by 161
  7. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 143
  8. 2021safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Roboticscited by 50

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
  2. 2025Domain-Agnostic Scalable AI Safety Ensuring Framework
  3. 2026CALOS: Control-Affine Lyapunov On-manifold Safety Layer for Safe Deep Reinforcement Learning for Quadrotors
  4. 2025Feasibility-Aware Pessimistic Estimation: Toward Long-Horizon Safety in Offline RL
  5. 2026LEAP-CBF: A Safety Filter for Uncertain Systems with Least-Effort Adversarial Potentials
  6. 2026TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning
  7. 2026CAPSULE: Control-Theoretic Action Perturbations for Safe Uncertainty-Aware Reinforcement Learning
  8. 2026Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation