# Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning

arXiv: https://arxiv.org/abs/2111.12953 · HTML: https://mlsanity.com/paper/2111.12953/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 49 references that are in the map.
- First posted on arXiv 25 Nov 2021.

## Builds on (most cited first, 26 of 26)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Reward Constrained Policy Optimization](https://mlsanity.com/paper/1805.11074/) (2018)
- [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019)
- [Safe Model-based Reinforcement Learning with Stability Guarantees](https://mlsanity.com/paper/1705.08551/) (2017)
- [Risk-Constrained Reinforcement Learning with Percentile Risk Criteria](https://mlsanity.com/paper/1512.01629/) (2015)
- [Responsive Safety in Reinforcement Learning by PID Lagrangian Methods](https://mlsanity.com/paper/2007.03964/) (2020)
- [End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks](https://mlsanity.com/paper/1903.08792/) (2019)
- [Safe Exploration in Continuous Action Spaces](https://mlsanity.com/paper/1801.08757/) (2018)
- [Projection-Based Constrained Policy Optimization](https://mlsanity.com/paper/2010.03152/) (2020)
- [A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems](https://mlsanity.com/paper/1705.01292/) (2017)
- [Provably Efficient Safe Exploration via Primal-Dual Policy Optimization](https://mlsanity.com/paper/2003.00534/) (2020)
- [Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning](https://mlsanity.com/paper/2001.08726/) (2020)
- [Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates](https://mlsanity.com/paper/2101.05436/) (2021)
- [OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World](https://mlsanity.com/paper/1709.07643/) (2017)
- [Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function](https://mlsanity.com/paper/2103.01556/) (2021)
- [Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety](https://mlsanity.com/paper/2105.10682/) (2021)
- [Open-Sourced Reinforcement Learning Environments for Surgical Robotics](https://mlsanity.com/paper/1903.02090/) (2019)
- [Safe Control Algorithms Using Energy Functions: A Unified Framework, Benchmark, and New Directions](https://mlsanity.com/paper/1908.01883/) (2019)
- [Numerically Stable Dynamic Bicycle Model for Discrete-time Control](https://mlsanity.com/paper/2011.09612/) (2020)
- [Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning](https://mlsanity.com/paper/2102.08539/) (2021)
- [Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model](https://mlsanity.com/paper/2102.11513/) (2021)

## Built on by (most cited first, 4 of 4)

- [State-wise Safe Reinforcement Learning: A Survey](https://mlsanity.com/paper/2302.03122/) (2023)
- [AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning](https://mlsanity.com/paper/2301.10339/) (2023)
- [Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach](https://mlsanity.com/paper/2304.04066/) (2023)
- [Safety Reinforced Model Predictive Control (SRMPC): Improving MPC with Reinforcement Learning for Motion Planning in Autonomous Driving](https://mlsanity.com/paper/2512.03774/) (2025)

## Abstract (arXiv)

In the trial-and-error mechanism of reinforcement learning (RL), a notorious contradiction arises when we expect to learn a safe policy: how to learn a safe policy without enough data and prior model about the dangerous region? Existing methods mostly use the posterior penalty for dangerous actions, which means that the agent is not penalized until experiencing danger. This fact causes that the agent cannot learn a zero-violation policy even after convergence. Otherwise, it would not receive any penalty and lose the knowledge about danger. In this paper, we propose the safe set actor-critic (SSAC) algorithm, which confines the policy update using safety-oriented energy functions, or the safety indexes. The safety index is designed to increase rapidly for potentially dangerous actions, which allows us to locate the safe set on the action space, or the control safe set. Therefore, we can identify the dangerous actions prior to taking them, and further obtain a zero constraint-violation policy after convergence.We claim that we can learn the energy function in a model-free manner similar to learning a value function. By using the energy function transition as the constraint objective, we formulate a constrained RL problem. We prove that our Lagrangian-based solutions make sure that the learned policy will converge to the constrained optimum under some assumptions. The proposed algorithm is evaluated on both the complex simulation environments and a hardware-in-loop (HIL) experiment with a real controller from the autonomous vehicle. Experimental results suggest that the converged policy in all environments achieves zero constraint violation and comparable performance with model-based baselines.