English
Related papers

Related papers: Approximate Shielding of Atari Agents for Safe Exp…

200 papers

Autonomous systems that rely on learned perception can make unsafe decisions when sensor readings are misclassified. We study shielding for this setting: given a proposed action, a shield blocks actions that could violate safety. We…

Artificial Intelligence · Computer Science 2026-04-23 William Scarbro , Ravi Mangal

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit…

Cryptography and Security · Computer Science 2025-11-21 Zhen Sun , Zongmin Zhang , Deqi Liang , Han Sun , Yule Liu , Yun Shen , Xiangshan Gao , Yilong Yang , Shuai Liu , Yutao Yue , Xinlei He

One of the main issues in Imitation Learning is the erroneous behavior of an agent when facing out-of-distribution situations, not covered by the set of demonstrations given by the expert. In this work, we tackle this problem by introducing…

Robotics · Computer Science 2020-11-20 Norman Di Palo , Edward Johns

Exploration algorithms for reinforcement learning typically replace or augment the reward function with an additional ``intrinsic'' reward that trains the agent to seek previously unseen states of the environment. Here, we consider an…

Machine Learning · Computer Science 2025-09-30 Kevin McKee , Eric Alt , Andrew Grebenisan , Mick van Gelderen , Gary Miguel

In the past few years, deep reinforcement learning has been proven to solve problems which have complex states like video games or board games. The next step of intelligent agents would be able to generalize between tasks, and using prior…

Machine Learning · Computer Science 2018-09-05 Shu-Hsuan Hsu , I-Chao Shen , Bing-Yu Chen

Recent advancements in large language models (LLMs) have expanded their capabilities beyond traditional text-based tasks to multimodal domains, integrating visual, auditory, and textual data. While multimodal LLMs have been extensively…

Artificial Intelligence · Computer Science 2024-12-03 Nicholas R. Waytowich , Devin White , MD Sunbeam , Vinicius G. Goecks

Multi-agent reinforcement learning (MARL) has been increasingly used in a wide range of safety-critical applications, which require guaranteed safety (e.g., no unsafe states are ever visited) during the learning process.Unfortunately,…

Machine Learning · Computer Science 2021-02-03 Ingy Elsayed-Aly , Suda Bharadwaj , Christopher Amato , Rüdiger Ehlers , Ufuk Topcu , Lu Feng

State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks. Learning such representations without supervision…

Machine Learning · Computer Science 2020-11-09 Ankesh Anand , Evan Racah , Sherjil Ozair , Yoshua Bengio , Marc-Alexandre Côté , R Devon Hjelm

Current approximate Coarse Correlated Equilibria (CCE) algorithms struggle with equilibrium approximation for games in large stochastic environments but are theoretically guaranteed to converge to a strong solution concept. In contrast,…

Machine Learning · Computer Science 2024-12-04 Ryan Yu , Mateusz Nowak , Qintong Xie , Michelle Yilin Feng , Peter Chin

Equipping artificial agents with useful exploration mechanisms remains a challenge to this day. Humans, on the other hand, seem to manage the trade-off between exploration and exploitation effortlessly. In the present article, we put…

Machine Learning · Computer Science 2022-11-15 Marcel Binz , Eric Schulz

We present a new model-based algorithm for reinforcement learning (RL) which consists of explicit exploration and exploitation phases, and is applicable in large or infinite state spaces. The algorithm maintains a set of dynamics models…

Machine Learning · Computer Science 2019-12-03 Mikael Henaff

Shielding is a prominent model-based technique to ensure safety of autonomous agents. Classical shielding aims to ensure that nothing bad ever happens and comes with strong guarantees about safety and maximal permissiveness. However,…

Logic in Computer Science · Computer Science 2026-05-14 Linus Heck , Filip Macák , Roman Andriushchenko , Milan Češka , Sebastian Junges

The infamous exploration-exploitation dilemma is one of the oldest and most important problems in reinforcement learning (RL). Deliberate and effective exploration is necessary for RL agents to succeed in most environments. However, until…

Artificial Intelligence · Computer Science 2017-10-09 Suraj Narayanan Sasikumar

Exploration is critical to a reinforcement learning agent's performance in its given environment. Prior exploration methods are often based on using heuristic auxiliary predictions to guide policy behavior, lacking a mathematically-grounded…

Machine Learning · Computer Science 2020-03-02 Lisa Lee , Benjamin Eysenbach , Emilio Parisotto , Eric Xing , Sergey Levine , Ruslan Salakhutdinov

The applicability of reinforcement learning (RL) algorithms in real-world domains often requires adherence to safety constraints, a need difficult to address given the asymptotic nature of the classic RL optimization objective. In contrast…

Machine Learning · Computer Science 2021-04-15 Moritz A. Zanger , Karam Daaboul , J. Marius Zöllner

Hybrid offline--online reinforcement learning (O2O RL) promises both sample efficiency and robust exploration, but suffers from instability due to distribution shift between offline and online data. We introduce RLPD-GX, a framework that…

Machine Learning · Computer Science 2025-10-28 Kaitong Cai , Jusheng Zhang , Jing Yang , Keze Wang

Model-based reinforcement learning is a powerful tool, but collecting data to fit an accurate model of the system can be costly. Exploring an unknown environment in a sample-efficient manner is hence of great importance. However, the…

Machine Learning · Computer Science 2023-04-27 Matthieu Blanke , Marc Lelarge

Agents operating in physical environments need to be able to handle delays in the input and output signals since neither data transmission nor sensing or actuating the environment are instantaneous. Shields are correct-by-construction…

Artificial Intelligence · Computer Science 2023-07-06 Filip Cano Córdoba , Alexander Palmisano , Martin Fränzle , Roderick Bloem , Bettina Könighofer

The ability to accurately predict others' behavior is central to the safety and efficiency of interactive robotics. Unfortunately, robots often lack access to key information on which these predictions may hinge, such as other agents'…

Robotics · Computer Science 2023-11-02 Haimin Hu , David Isele , Sangjae Bae , Jaime F. Fisac

Safe exploration presents a major challenge in reinforcement learning (RL): when active data collection requires deploying partially trained policies, we must ensure that these policies avoid catastrophically unsafe regions, while still…

Machine Learning · Computer Science 2021-04-27 Homanga Bharadhwaj , Aviral Kumar , Nicholas Rhinehart , Sergey Levine , Florian Shkurti , Animesh Garg