Dynamic Shielding for Reinforcement Learning in Black-Box Environments

2022-07-27 · Masaki Waga, Ezequiel Castellano, Sasinee Pruekprasert, Stefan Klikovits, Toru Takisaka, Ichiro Hasuo

It is challenging to use reinforcement learning (RL) in cyber-physical systems due to the lack of safety guarantees during learning. Although there have been various proposals to reduce undesired behaviors during learning, most of these techniques require prior system knowledge, and their applicability is limited. This paper aims to reduce undesired behaviors during learning without requiring any prior system knowledge. We propose dynamic shielding: an extension of a model-based safe RL technique called shielding using automata learning. The dynamic shielding technique constructs an approximate system model in parallel with RL using a variant of the RPNI algorithm and suppresses undesired explorations due to the shield constructed from the learned model. Through this combination, potentially unsafe actions can be foreseen before the agent experiences them. Experiments show that our dynamic shield significantly decreases the number of undesired events during training.

📄 PDF Abstract BibTeX arXiv:2207.13446

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding

2024-05-28 · Daniel Bethell, Simos Gerasimou, Radu Calinescu, Calum Imrie

Empowering safe exploration of reinforcement learning (RL) agents during training is a critical challenge towards their deployment in many real-world scenarios. When prior knowledge of the domain or task is unavailable, …

reinforcement-learning Reinforcement Learning (RL)Safe Exploration Safe Reinforcement Learning

Learning-Based Shielding for Safe Autonomy under Unknown Dynamics

2024-10-07 · Robert Reed, Morteza Lahijanian

Shielding is a common method used to guarantee the safety of a system under a black-box controller, such as a neural network controller from deep reinforcement learning (DRL), with simpler, verified controllers. Existing…

Deep Reinforcement Learning Uncertainty Quantification

Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning

2023-04-13 · Wenli Xiao, Yiwei Lyu, John Dolan

Multi-Agent Reinforcement Learning (MARL) discovers policies that maximize reward but do not have safety guarantees during the learning and deployment phases. Although shielding with Linear Temporal Logic (LTL) is a prom…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments

2024-02-01 · Alexander W. Goodall, Francesco Belardinelli

Shielding is a popular technique for achieving safe reinforcement learning (RL). However, classical shielding approaches come with quite restrictive assumptions making them difficult to deploy in complex environments, pa…

Reinforcement Learning (RL)Safe Reinforcement Learning

Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models

2026-02-12 · Alexander W. Goodall, Francesco Belardinelli arxiv

Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications. In this paper, we introduce a novel recovery-based shieldi…

Reinforcement Learning Continuous Control