mlsanityData to 14 Oct 2026

Physical Deep Reinforcement Learning Towards Safety Guarantee

arXiv 2303.16860 ↗First posted 29 Mar 2023cs.LG cs.SY eess.SYcited by 3

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning (DRL) has achieved tremendous success in many complex decision-making tasks of autonomous systems with high-dimensional state and/or action spaces. However, the safety and stability still remain major concerns that hinder the applications of DRL to safety-critical autonomous systems. To address the concerns, we proposed the Phy-DRL: a physical deep reinforcement learning framework. The Phy-DRL is novel in two architectural designs: i) Lyapunov-like reward, and ii) residual control (i.e., integration of physics-model-based control and data-driven control). The concurrent physical reward and residual control empower the Phy-DRL the (mathematically) provable safety and stability guarantees. Through experiments on the inverted pendulum, we show that the Phy-DRL features guaranteed safety and stability and enhanced robustness, while offering remarkably accelerated training and enlarged reward.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 14 of its 27 references that are in the map. First posted on arXiv 29 Mar 2023.

Builds on

14 of 27 references.

References · 14

  1. 2015Continuous control with deep reinforcement learningcited by 3,407
  2. 2016OpenAI Gymcited by 1,736
  3. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  4. 2017Safe Reinforcement Learning via Shieldingcited by 449
  5. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  6. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  7. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 289
  8. 2018Learning to Drive in a Daycited by 273
  9. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 163
  10. 2020Safe Reinforcement Learning in Constrained Markov Decision Processescited by 115
  11. 2021Stabilizing Neural Control Using Self-Learned Almost Lyapunov Criticscited by 35
  12. 2022Lyapunov Design for Robust and Efficient Robotic Reinforcement Learningcited by 28
2 more
  1. 2022Quantifying Safety of Learning-based Self-Driving Control Using Almost-Barrier Functionscited by 10
  2. 2020SL1-Simplex: Safe Velocity Regulation of Self-Driving Vehicles in Dynamic and Unforeseen Environmentscited by 9

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2023A Survey on Physics Informed Reinforcement Learning: Review and Open Problemscited by 24
  2. 2023Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approachcited by 13
  3. 2024Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equationscited by 3