Guided Safe Shooting: model based reinforcement learning with safety constraints

2022-06-20 · Giuseppe Paolo, Jonas Gonzalez-Billandon, Albert Thomas, Balázs Kégl

In the last decade, reinforcement learning successfully solved complex control tasks and decision-making problems, like the Go board game. Yet, there are few success stories when it comes to deploying those algorithms to real-world scenarios. One of the reasons is the lack of guarantees when dealing with and avoiding unsafe states, a fundamental requirement in critical control engineering systems. In this paper, we introduce Guided Safe Shooting (GuSS), a model-based RL approach that can learn to control systems with minimal violations of the safety constraints. The model is learned on the data collected during the operation of the system in an iterated batch fashion, and is then used to plan for the best action to perform at each time step. We propose three different safe planners, one based on a simple random shooting strategy and two based on MAP-Elites, a more advanced divergent-search algorithm. Experiments show that these planners help the learning agent avoid unsafe situations while maximally exploring the state space, a necessary aspect when learning an accurate model of the system. Furthermore, compared to model-free approaches, learning a model allows GuSS reducing the number of interactions with the real-system while still reaching high rewards, a fundamental requirement when handling engineering systems.

📄 PDF Abstract BibTeX arXiv:2206.09743

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingModel-based Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics

2024-05-24 · David Boetius, Stefan Leue

Naively trained Deep Reinforcement Learning agents may fail to satisfy vital safety constraints. To avoid costly retraining, we may desire to repair a previously trained reinforcement learning agent to obviate unsafe beh…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning

Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning

2021-02-17 · Baiyu Peng, Yao Mu, Jingliang Duan, Yang Guan 외

Safety is essential for reinforcement learning (RL) applied in real-world tasks like autonomous driving. Chance constraints which guarantee the satisfaction of state constraints at a high probability are suitable to repr…

Autonomous Driving reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Epigraph-Guided Flow Matching for Safe and Performant Offline Reinforcement Learning

2026-02-08 · Manan Tayal, Mumuksh Tayal arxiv

Offline reinforcement learning (RL) provides a compelling paradigm for training autonomous systems without the risks of online exploration, particularly in safety-critical domains. However, jointly achieving strong safet…

Reinforcement Learning Offline RL

SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics

2022-04-20 · Yannis Flet-Berliac, Debabrota Basu

Although Reinforcement Learning (RL) is effective for sequential decision-making problems under uncertainty, it still fails to thrive in real-world systems where risk or safety is a binding constraint. In this paper, we …

continuous-control Continuous Control Decision Making reinforcement-learning+5

Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints

2026-05-13 · Timofey Tomashevskiy arxiv

Safe reinforcement learning in nonstationary environments requires safety mechanisms that adapt as environmental conditions change. Standard safe reinforcement learning methods often assume fixed constraints or stable en…

Reinforcement Learning