Safe Exploration for Interactive Machine Learning

2019-10-30 · NeurIPS 2019 12 · Matteo Turchetta, Felix Berkenkamp, Andreas Krause

In Interactive Machine Learning (IML), we iteratively make decisions and obtain noisy observations of an unknown function. While IML methods, e.g., Bayesian optimization and active learning, have been successful in applications, on real-world systems they must provably avoid unsafe decisions. To this end, safe IML algorithms must carefully learn about a priori unknown constraints without making unsafe decisions. Existing algorithms for this problem learn about the safety of all decisions to ensure convergence. This is sample-inefficient, as it explores decisions that are not relevant for the original IML objective. In this paper, we introduce a novel framework that renders any existing unsafe IML algorithm safe. Our method works as an add-on that takes suggested decisions as input and exploits regularity assumptions in terms of a Gaussian process prior in order to efficiently learn about their safety. As a result, we only explore the safe set when necessary for the IML problem. We apply our framework to safe Bayesian optimization and to safe exploration in deterministic Markov Decision Processes (MDP), which have been analyzed separately before. Our method outperforms other algorithms empirically.

📄 PDF Abstract BibTeX arXiv:1910.13726

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningBayesian OptimizationBIG-bench Machine LearningSafe Exploration

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors

2023-02-25 · Shangding Gu, Alap Kshirsagar, Yali Du, Guang Chen 외

Deployment of Reinforcement Learning (RL) algorithms for robotics applications in the real world requires ensuring the safety of the robot and its environment. Safe Robot RL (SRRL) is a crucial step towards achieving hum…

reinforcement-learning Reinforcement Learning (RL)Safe Exploration

Dialogue based Interactive Explanations for Safety Decisions in Human Robot Collaboration

2026-04-07 · Yifan Xu, Xiao Zhan, Akilu Yunusa Kaltungo, Ming Shan Ng 외 arxiv

As robots increasingly operate in shared, safety critical environments, acting safely is no longer sufficient robots must also make their safety decisions intelligible to human collaborators. In human robot collaboration…

Safe Interactive Model-Based Learning

2019-11-15 · Marco Gallieri, Seyed Sina Mirrazavi Salehian, Nihat Engin Toklu, Alessio Quaglino 외

Control applications present hard operational constraints. A violation of these can result in unsafe behavior. This paper introduces Safe Interactive Model Based Learning (SiMBL), a framework to refine an existing contro…

model Safe Exploration

SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model

2026-06-15 · Kai Tang, Peidong Jia, Zhong Chu, Jixian Wu 외 arxiv

Safe control is a prerequisite for real-world embodied intelligence, for which safe reinforcement learning has emerged as a promising paradigm. However, existing safe reinforcement learning methods either require costly …

Reinforcement Learning

Explore-Exploit: A Framework for Interactive and Online Learning

2018-12-01 · Honglei Liu, Anuj Kumar, Wenhai Yang, Benoit Dumoulin

Interactive user interfaces need to continuously evolve based on the interactions that a user has (or does not have) with the system. This may require constant exploration of various options that the system may have for …

Active Learning