English
Related papers

Related papers: Oracle-Guided Soft Shielding for Safe Move Predict…

200 papers

Detecting out-of-distribution (OOD) graphs is crucial for ensuring the safety and reliability of Graph Neural Networks. In unsupervised graph-level OOD detection, models are typically trained using only in-distribution (ID) data, resulting…

Machine Learning · Computer Science 2026-03-03 Li Sun , Lanxu Yang , Jiayu Tian , Bowen Fang , Xiaoyan Yu , Junda Ye , Peng Tang , Hao Peng , Philip S. Yu

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…

Machine Learning · Computer Science 2019-10-31 Matteo Turchetta , Felix Berkenkamp , Andreas Krause

Accurate and robust trajectory prediction is essential for safe and efficient autonomous driving, yet recent work has shown that even state-of-the-art prediction models are highly vulnerable to inputs being mildly perturbed by adversarial…

We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from operating in an environment, in order to learn to achieve a challenging control goal (e.g., an agile…

Machine Learning · Computer Science 2020-06-30 Anqi Liu , Guanya Shi , Soon-Jo Chung , Anima Anandkumar , Yisong Yue

Prior access to domain knowledge could significantly improve the performance of a reinforcement learning agent. In particular, it could help agents avoid potentially catastrophic exploratory actions, which would otherwise have to be…

Artificial Intelligence · Computer Science 2020-09-15 Thommen George Karimpanal , Santu Rana , Sunil Gupta , Truyen Tran , Svetha Venkatesh

We have seen numerous machine learning methods tackle the game of chess over the years. However, one common element in these works is the necessity of a finely optimized look ahead algorithm. The particular interest of this research lies…

Artificial Intelligence · Computer Science 2020-07-07 Arman Maesumi

We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a…

Machine Learning · Computer Science 2018-11-22 Jessie Huang , Fa Wu , Doina Precup , Yang Cai

This paper introduces the reinforcement learning backup shield (RLBUS), an algorithm that guarantees safe exploration in reinforcement learning (RL) by incorporating backup control barrier functions (BCBFs). RLBUS constructs an implicit…

Systems and Control · Electrical Eng. & Systems 2024-12-10 Pedram Rabiee , Amirsaeid Safari

Reward shaping is critical in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. However, choosing effective shaping rewards from a set of reward functions in a computationally efficient…

Machine Learning · Computer Science 2025-02-26 Chen Bo Calvin Zhang , Zhang-Wei Hong , Aldo Pacchiano , Pulkit Agrawal

Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these…

Robotics · Computer Science 2024-03-05 Chenyang Cao , Zichen Yan , Renhao Lu , Junbo Tan , Xueqian Wang

Chess, a deterministic game with perfect information, has long served as a benchmark for studying strategic decision-making and artificial intelligence. Traditional chess engines or tools for analysis primarily focus on calculating optimal…

Artificial Intelligence · Computer Science 2025-12-02 Daren Zhong , Dingcheng Huang , Clayton Greenberg

Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk of catastrophic…

Machine Learning · Computer Science 2023-10-31 Marc Rigter , Bruno Lacerda , Nick Hawes

Imitation of expert behaviour is a highly desirable and safe approach to the problem of sequential decision making. We provide an easy-to-implement, novel algorithm for imitation learning under a strict data paradigm, in which the agent…

Machine Learning · Computer Science 2023-02-07 Matthew Smith , Lucas Maystre , Zhenwen Dai , Kamil Ciosek

Object navigation is defined as navigating to an object of a given label in a complex, unexplored environment. In its general form, this problem poses several challenges for Robotics: semantic exploration of unknown environments in search…

Robotics · Computer Science 2020-07-31 Ayzaan Wahid , Austin Stone , Kevin Chen , Brian Ichter , Alexander Toshev

Game theory provides a mathematical way to study the interaction between multiple decision makers. However, classical game-theoretic analysis is limited in scalability due to the large number of strategies, precluding direct application to…

Computer Science and Game Theory · Computer Science 2024-05-28 Ariyan Bighashdel , Yongzhao Wang , Stephen McAleer , Rahul Savani , Frans A. Oliehoek

The sparsity of reward feedback remains a challenging problem in online deep reinforcement learning (DRL). Previous approaches have utilized offline demonstrations to achieve impressive results in multiple hard tasks. However, these…

Machine Learning · Computer Science 2024-10-28 Guojian Wang , Faguo Wu , Xiao Zhang , Tianyuan Chen

Reinforcement Learning (RL) has gained significant attention across various domains. However, the increasing complexity of RL programs presents testing challenges, particularly the oracle problem: defining the correctness of the RL program.…

Software Engineering · Computer Science 2024-07-01 Shiyu Zhang , Haoyang Song , Qixin Wang , Yu Pei

In environments with uncertain dynamics exploration is necessary to learn how to perform well. Existing reinforcement learning algorithms provide strong exploration guarantees, but they tend to rely on an ergodicity assumption. The essence…

Machine Learning · Computer Science 2012-07-10 Teodor Mihai Moldovan , Pieter Abbeel

Methods that extract policy primitives from offline demonstrations using deep generative models have shown promise at accelerating reinforcement learning(RL) for new tasks. Intuitively, these methods should also help to trainsafeRLagents…

Machine Learning · Computer Science 2022-07-04 Dylan Slack , Yinlam Chow , Bo Dai , Nevan Wichers

The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance, frequently without considering safety. In contrast, safe reinforcement learning seeks to reduce or avoid unsafe behavior.…

Machine Learning · Computer Science 2025-06-17 Zahra Shahrooei , Ali Baheri
‹ Prev 1 4 5 6 7 8 10 Next ›