mlsanityData to 7 Oct 2026

Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems

arXiv 2404.15199 ↗First posted 23 Apr 2024cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Reinforcement Learning (RL) is a powerful method for controlling dynamic systems, but its learning mechanism can lead to unpredictable actions that undermine the safety of critical systems. Here, we propose RL with Adaptive Regularization (RL-AR), an algorithm that enables safe RL exploration by combining the RL policy with a policy regularizer that hard-codes the safety constraints. RL-AR performs policy combination via a "focus module," which determines the appropriate combination depending on the state--relying more on the safe policy regularizer for less-exploited states while allowing unbiased convergence for well-exploited states. In a series of critical control applications, we demonstrate that RL-AR not only ensures safety during training but also achieves a return competitive with the standards of model-free RL that disregards safety.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 23 of its 54 references that are in the map. First posted on arXiv 23 Apr 2024.

Builds on

23 of 54 references.

References · 23

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  5. 2017Constrained Policy Optimizationcited by 928
  6. 2017Deep Reinforcement Learning that Matterscited by 727
  7. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
  8. 2020Projection-Based Constrained Policy Optimizationcited by 195
  9. 2018Residual Policy Learningcited by 146
  10. 2018A Tour of Reinforcement Learning: The View from Continuous Controlcited by 129
  11. 2020Conservative Safety Critics for Explorationcited by 107
  12. 2022Constrained Variational Policy Optimization for Safe Reinforcement Learningcited by 69
11 more
  1. 2019Data-driven Economic NMPC using Reinforcement Learningcited by 55
  2. 2022Reachability Constrained Reinforcement Learningcited by 52
  3. 2020Neurosymbolic Reinforcement Learning with Formally Verified Explorationcited by 49
  4. 2019Control Regularization for Reduced Variance Reinforcement Learningcited by 34
  5. 2022Towards Safe Reinforcement Learning with a Safety Editor Policycited by 28
  6. 2020Deep Reinforcement Learning for Closed-Loop Blood Glucose Controlcited by 26
  7. 2022You Only Live Once: Single-Life Reinforcement Learningcited by 23
  8. 2022Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopescited by 23
  9. 2019Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learningcited by 7
  10. 2019Driving Reinforcement Learning with Modelscited by 3
  11. 2020Reinforcement Learning Based on Real-Time Iteration NMPCcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2026Can RL Improve Generalization of LLM Agents? An Empirical Studycited by 4
  2. 2025A Novel Framework for Uncertainty-Driven Adaptive Explorationcited by 1
  3. 2025Mission-Aligned Learning-Informed Control of Autonomous Systems: Formulation and Foundationscited by 0
  4. 2025Constraint-Aware Reinforcement Learning via Adaptive Action Scalingcited by 0
  5. 2026Safe Online Learning via Smooth Safety-Structured Policy Compositioncited by 0
  6. 2026HetGPS: Scalable Graph Multi-Agent Reinforcement Learning with Physics-Anchored Adaptive Safety for EV Chargingcited by 0