mlsanityData to 14 Oct 2026

mathrmE2CFD: Towards Effective and Efficient Cost Function Design for Safe Reinforcement Learning via Large Language Model

arXiv 2407.05580 ↗First posted 8 Jul 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Different classes of safe reinforcement learning algorithms have shown satisfactory performance in various types of safety requirement scenarios. However, the existing methods mainly address one or several classes of specific safety requirement scenario problems and cannot be applied to arbitrary safety requirement scenarios. In addition, the optimization objectives of existing reinforcement learning algorithms are misaligned with the task requirements. Based on the need to address these issues, we propose mathrmE2CFD, an effective and efficient cost function design framework. mathrmE2CFD leverages the capabilities of a large language model (LLM) to comprehend various safety scenarios and generate corresponding cost functions. It incorporates the textitfast performance evaluation (FPE) method to facilitate rapid and iterative updates to the generated cost function. Through this iterative process, mathrmE2CFD aims to obtain the most suitable cost function for policy training, tailored to the specific tasks within the safety scenario. Experiments have proven that the performance of policies trained using this framework is superior to traditional safe reinforcement learning algorithms and policies trained with carefully designed cost functions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 8 Jul 2024.

Builds on

25 of 36 references.

References · 25

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  3. 2017Constrained Policy Optimizationcited by 983
  4. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 571
  5. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 316
  6. 2023Language to Rewards for Robotic Skill Synthesiscited by 312
  7. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 297
  8. 2023Reward Design with Language Modelscited by 261
  9. 2018Safe Exploration in Continuous Action Spacescited by 247
  10. 2020Projection-Based Constrained Policy Optimizationcited by 203
  11. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 143
  12. 2024Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methodscited by 116
13 more
  1. 2019Using Natural Language for Reward Shaping in Reinforcement Learningcited by 114
  2. 2018On Learning Intrinsic Rewards for Policy Gradient Methodscited by 102
  3. 2019Safe Policies for Reinforcement Learning via Primal-Dual Methodscited by 79
  4. 2021Towards Long-term Fairness in Recommendationcited by 77
  5. 2022Constrained Update Projection Approach to Safe Policy Optimizationcited by 58
  6. 2019Safe Reinforcement Learning on Autonomous Vehiclescited by 50
  7. 2021ELLA: Exploration through Learned Language Abstractioncited by 42
  8. 2019Evolving Rewards to Automate Reinforcement Learningcited by 31
  9. 2018Resource Constrained Deep Reinforcement Learningcited by 24
  10. 2022EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RLcited by 23
  11. 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learningcited by 18
  12. 2023AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learningcited by 17
  13. 2020Language-Conditioned Goal Generation: a New Approach to Language Grounding for RLcited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewards
  2. 2026Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data
  3. 2024Revisiting Safe Exploration in Safe Reinforcement learning
  4. 2025CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
  5. 2024Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints
  6. 2025A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions
  7. 2024Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization
  8. 2024Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning