paper-with-me

Papers

Guiding Safe Exploration with Weakest Preconditions

2022-09-28 · Greg Anderson, Swarat Chaudhuri, Isil Dillig

In reinforcement learning for safety-critical settings, it is often desirable for the agent to obey safety constraints at all points in time, including during training. We present a novel neurosymbolic approach called SPICE to solve this safe exploration problem. SPICE uses an online shielding layer based on symbolic weakest preconditions to achieve a more precise safety analysis than existing tools without unduly impacting the training process. We evaluate the approach on a suite of continuous control benchmarks and show that it can achieve comparable performance to existing safe learning techniques while incurring fewer safety violations. Additionally, we present theoretical results showing that SPICE converges to the optimal safe policy under reasonable assumptions.

📄 PDF Abstract BibTeX arXiv:2209.14148

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning (RL)Safe Exploration

Similar Papers 제목 키워드 기반

LLMs and Fuzzing in Tandem: A New Approach to Automatically Generating Weakest Preconditions

2025-07-03 · Daragh King, Vasileios Koutavas, Laura Kovacs arxiv

The weakest precondition (WP) of a program describes the largest set of initial states from which all terminating executions of the program satisfy a given postcondition. The generation of WPs is an important task with p…

Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment

2024-01-26 · Shibbir Ahmed, Hongyang Gao, Hridesh Rajan

Deep learning models are trained with certain assumptions about the data during the development stage and then used for prediction in the deployment stage. It is important to reason about the trustworthiness of the model…

Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version)

2023-07-10 · Xiaotong Ji, Antonio Filieri

Safe exploration aims at addressing the limitations of Reinforcement Learning (RL) in safety-critical scenarios, where failures during trial-and-error learning may incur high costs. Several methods exist to incorporate e…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Exploration

Safe Active Navigation and Exploration for Planetary Environments Using Proprioceptive Measurements

2025-10-21 · Matthew Jiang, Shipeng Liu, Feifei Qian arxiv

Legged robots can sense terrain through force interactions during locomotion, offering more reliable traversability estimates than remote sensing and serving as scouts for guiding wheeled rovers in challenging environmen…

Validating Generalist Robots with Situation Calculus and STL Falsification

2026-01-06 · Changwen Li, Rongjie Yan, Chih-Hong Cheng, Jian Zhang arxiv

Generalist robots are becoming a reality, capable of interpreting natural language instructions and executing diverse operations. However, their validation remains challenging because each task induces its own operationa…