paper-with-me

Papers

Safe Exploration for Identifying Linear Systems via Robust Optimization

2017-11-30 · Tyler Lu, Martin Zinkevich, Craig Boutilier, Binz Roy, Dale Schuurmans

Safely exploring an unknown dynamical system is critical to the deployment of reinforcement learning (RL) in physical systems where failures may have catastrophic consequences. In scenarios where one knows little about the dynamics, diverse transition data covering relevant regions of state-action space is needed to apply either model-based or model-free RL. Motivated by the cooling of Google's data centers, we study how one can safely identify the parameters of a system model with a desired accuracy and confidence level. In particular, we focus on learning an unknown linear system with Gaussian noise assuming only that, initially, a nominal safe action is known. Define safety as satisfying specific linear constraints on the state space (e.g., requirements on process variable) that must hold over the span of an entire trajectory, and given a Probably Approximately Correct (PAC) style bound on the estimation error of model parameters, we show how to compute safe regions of action space by gradually growing a ball around the nominal safe action. One can apply any exploration strategy where actions are chosen from such safe regions. Experiments on a stylized model of data center cooling dynamics show how computing proper safe regions can increase the sample efficiency of safe exploration.

📄 PDF Abstract BibTeX arXiv:1711.11165

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningReinforcement Learning (RL)Safe Exploration

Similar Papers 제목 키워드 기반

Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems

2020-05-09 · Yashwanth Kumar Nakka, Anqi Liu, Guanya Shi, Anima Anandkumar 외

Learning-based control algorithms require data collection with abundant supervision for training. Safe exploration algorithms ensure the safety of this data collection process even when only partial knowledge is availabl…

Motion PlanningOptimal Motion PlanningSafe Exploration

Safe Policy Optimization with Local Generalized Linear Function Approximations

2021-11-09 · NeurIPS 2021 12 · Akifumi Wachi, Yunyue Wei, Yanan Sui

Safe exploration is a key to applying reinforcement learning (RL) in safety-critical systems. Existing safe exploration methods guaranteed safety under the assumption of regularity, and it has been difficult to apply the…

Reinforcement Learning (RL)Safe Exploration

Safe Guaranteed Exploration for Non-linear Systems

2024-02-09 · Manish Prajapat, Johannes Köhler, Matteo Turchetta, Andreas Krause 외

Safely exploring environments with a-priori unknown constraints is a fundamental challenge that restricts the autonomy of robots. While safety is paramount, guarantees on sufficient exploration are also crucial for ensur…

Efficient ExplorationModel Predictive Control

MPC-Guided Safe Reinforcement Learning and Lipschitz-Based Filtering for Structured Nonlinear Systems

2025-12-14 · Patrick Kostelac, Xuerui Wang, Anahita Jamshidnejad arxiv

Modern engineering systems, such as autonomous vehicles, flexible robotics, and intelligent aerospace platforms, require controllers that are robust to uncertainties, adaptive to environmental changes, and safety-aware u…

Reinforcement LearningAutonomous Vehicles

GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems

2022-01-24 · Bhavya Sukhija, Matteo Turchetta, David Lindner, Andreas Krause 외

Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage. Most existing model-free learning methods that guarantee safety, i.e., no fail…

global-optimizationSafe Exploration