# SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints

arXiv: https://arxiv.org/abs/2512.23770 · HTML: https://mlsanity.com/paper/2512.23770/

## 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 23 of its 36 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Reward Constrained Policy Optimization](https://mlsanity.com/paper/1805.11074/) (2018)
- [Safe Model-based Reinforcement Learning with Stability Guarantees](https://mlsanity.com/paper/1705.08551/) (2017)
- [Responsive Safety in Reinforcement Learning by PID Lagrangian Methods](https://mlsanity.com/paper/2007.03964/) (2020)
- [A Lyapunov-based Approach to Safe Reinforcement Learning](https://mlsanity.com/paper/1805.07708/) (2018)
- [Projection-Based Constrained Policy Optimization](https://mlsanity.com/paper/2010.03152/) (2020)
- [Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark](https://mlsanity.com/paper/2310.12567/) (2023)
- [CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee](https://mlsanity.com/paper/2011.05869/) (2020)
- [Penalized Proximal Policy Optimization for Safe Reinforcement Learning](https://mlsanity.com/paper/2205.11814/) (2022)
- [Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments](https://mlsanity.com/paper/2209.15090/) (2022)
- [Constrained Update Projection Approach to Safe Policy Optimization](https://mlsanity.com/paper/2209.07089/) (2022)
- [A Survey of Constraint Formulations in Safe Reinforcement Learning](https://mlsanity.com/paper/2402.02025/) (2024)
- [Towards Safe Reinforcement Learning with a Safety Editor Policy](https://mlsanity.com/paper/2201.12427/) (2022)
- [Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm](https://mlsanity.com/paper/2210.07573/) (2022)
- [Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation](https://mlsanity.com/paper/2405.01677/) (2024)
- [Probabilistic Shielding for Safe Reinforcement Learning](https://mlsanity.com/paper/2503.07671/) (2025)
- [Embedding Safety into RL: A New Take on Trust Region Methods](https://mlsanity.com/paper/2411.02957/) (2024)
- [An Analytical Update Rule for General Policy Optimization](https://mlsanity.com/paper/2112.02045/) (2021)
- [Central Path Proximal Policy Optimization](https://mlsanity.com/paper/2506.00700/) (2025)

## Abstract (arXiv)

In safety-critical domains, reinforcement learning (RL) systems must satisfy strict, zero-cost safety constraints while achieving meaningful task performance. Existing model-free methods can struggle to achieve high safety without substantially compromising task performance. We introduce Safety-Biased Trust Region Policy Optimisation (SB-TRPO), a principled approach to RL with zero-cost constraints, which requires only a fixed fraction of the maximal cost reduction achievable within the trust region, thus retaining flexibility for reward optimisation. We show that the idealised update nevertheless converges to zero cost and maximal reward amongst zero-cost policies in finite MDPs. A practical gradient-based approximation provides local improvements in both safety and reward under suitable gradient alignment. Experiments on Safety Gymnasium demonstrate high safety alongside strong task performance.