paper-with-me

홈 › Papers

Lyapunov-based Safe Policy Optimization for Continuous Control

2019-01-28 · Yin-Lam Chow, Ofir Nachum, Aleksandra Faust, Edgar Duenez-Guzman, Mohammad Ghavamzadeh

We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to undesirable situations. We formulate these problems as constrained Markov decision processes (CMDPs) and present safe policy optimization algorithms that are based on a Lyapunov approach to solve them. Our algorithms can use any standard policy gradient (PG) method, such as deep deterministic policy gradient (DDPG) or proximal policy optimization (PPO), to train a neural network policy, while guaranteeing near-constraint satisfaction for every policy update by projecting either the policy parameter or the action onto the set of feasible solutions induced by the state-dependent linearized Lyapunov constraints. Compared to the existing constrained PG algorithms, ours are more data efficient as they are able to utilize both on-policy and off-policy data. Moreover, our action-projection algorithm often leads to less conservative policy updates and allows for natural integration into an end-to-end PG training pipeline. We evaluate our algorithms and compare them with the state-of-the-art baselines on several simulated (MuJoCo) tasks, as well as a real-world indoor robot navigation problem, demonstrating their effectiveness in terms of balancing performance and constraint satisfaction. Videos of the experiments can be found in the following link: https://drive.google.com/file/d/1pzuzFqWIE710bE2U6DmS59AfRzqK2Kek/view?usp=sharing.

📄 PDF Abstract BibTeX arXiv:1901.10031

Code (1)

jemaw/gym-safety

Tasks

continuous-controlContinuous ControlMuJoCoReinforcement LearningRobot Navigation

Similar Papers 제목 키워드 기반

Lyapunov-Aware Quantum-Inspired Reinforcement Learning for Continuous-Time Vehicle Control: A Feasibility Study

2025-10-21 · Nutkritta Kraipatthanapong, Natthaphat Thathong, Pannita Suksawas, Thanunnut Klunklin 외 arxiv

This paper presents a novel Lyapunov-Based Quantum Reinforcement Learning (LQRL) framework that integrates quantum policy optimization with Lyapunov stability analysis for continuous-time vehicle control. The proposed ap…

Reinforcement Learning

Safe reinforcement learning control for continuous-time nonlinear systems without a backup controller

2022-09-19 · Soutrik Bandyopadhyay, Shubhendu Bhasin

This paper proposes an on-policy reinforcement learning (RL) control algorithm that solves the optimal regulation problem for a class of uncertain continuous-time nonlinear systems under user-defined state constraints. W…

reinforcement-learningReinforcement Learning (RL)Safe Reinforcement Learning

Lyapunov-based Safe Policy Optimization

2018-09-27 · Yinlam Chow, Ofir Nachum, Mohammad Ghavamzadeh, Edgar Guzman-Duenez

In many reinforcement learning applications, it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to certain undesirable situations. These prob…

Safe Policy Learning for Continuous Control

2019-09-25 · Yinlam Chow, Ofir Nachum, Aleksandra Faust, Edgar Duenez-Guzman 외

We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that keep the agent in desirable situations, both…

continuous-controlContinuous ControlMuJoCo

Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance

2026-05-11 · Adam Haroon, Erick J. Rodríguez-Seda, Cody Fleming, Tristan Schuler arxiv

Safe reinforcement learning (RL) typically asks $\textit{what}$ an agent should do. We ask $\textit{when}$ it needs to act, and show that a single policy can jointly learn control inputs and communication-efficient timin…

Reinforcement Learning