English
Related papers

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

200 papers

We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adversary publishes a seemingly well-behaved policy which in fact…

Machine Learning · Computer Science 2022-11-22 Shubham Kumar Bharti , Xuezhou Zhang , Adish Singla , Xiaojin Zhu

As modern games continue growing both in size and complexity, it has become more challenging to ensure that all the relevant content is tested and that any potential issue is properly identified and fixed. Attempting to maximize testing…

Machine Learning · Computer Science 2021-06-25 Camilo Gordillo , Joakim Bergdahl , Konrad Tollmar , Linus Gisslén

Reinforcement learning algorithms discover policies that maximize reward, but do not necessarily guarantee safety during learning or execution phases. We introduce a new approach to learn optimal policies while enforcing properties…

Logic in Computer Science · Computer Science 2017-09-05 Mohammed Alshiekh , Roderick Bloem , Ruediger Ehlers , Bettina Könighofer , Scott Niekum , Ufuk Topcu

Safety is still one of the major research challenges in reinforcement learning (RL). In this paper, we address the problem of how to avoid safety violations of RL agents during exploration in probabilistic and partially unknown…

Machine Learning · Computer Science 2022-12-06 Martin Tappler , Stefan Pranger , Bettina Könighofer , Edi Muškardin , Roderick Bloem , Kim Larsen

Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where…

Machine Learning · Computer Science 2022-02-17 Garrett Thomas , Yuping Luo , Tengyu Ma

A precondition for the deployment of a Reinforcement Learning agent to a real-world system is to provide guarantees on the learning process. While a learning algorithm will eventually converge to a good policy, there are no guarantees on…

Machine Learning · Statistics 2023-12-27 Paul Daoudi , Mathias Formoso , Othman Gaizi , Achraf Azize , Evrard Garcelon

Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model uses a soft, top-down attention mechanism to create a bottleneck in…

Machine Learning · Computer Science 2019-06-07 Alex Mott , Daniel Zoran , Mike Chrzanowski , Daan Wierstra , Danilo J. Rezende

Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in…

Machine Learning · Statistics 2019-06-17 Elena Smirnova , Elvis Dohmatob , Jérémie Mary

Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical…

Artificial Intelligence · Computer Science 2015-11-23 Bradly C. Stadie , Sergey Levine , Pieter Abbeel

Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) environments. In this work, we tackle this challenge by utilizing suboptimal yet conservative…

Machine Learning · Computer Science 2026-02-10 Manuel Wendl , Yarden As , Manish Prajapat , Anton Pollak , Stelian Coros , Andreas Krause

This paper investigates whether learning contingency-awareness and controllable aspects of an environment can lead to better exploration in reinforcement learning. To investigate this question, we consider an instantiation of this…

Machine Learning · Computer Science 2019-03-05 Jongwook Choi , Yijie Guo , Marcin Moczulski , Junhyuk Oh , Neal Wu , Mohammad Norouzi , Honglak Lee

How to detect and mitigate deceptive AI systems is an open problem for the field of safe and trustworthy AI. We analyse two algorithms for mitigating deception: The first is based on the path-specific objectives framework where paths in the…

Artificial Intelligence · Computer Science 2023-06-27 Ismail Sahbane , Francis Rhys Ward , C Henrik Åslund

Autonomous exploration of obstacle-rich spaces requires strategies that ensure efficiency while guaranteeing safety against collisions with obstacles. This paper investigates a novel platform-agnostic reinforcement learning framework that…

Robotics · Computer Science 2025-11-20 Gabriele Calzolari , Vidya Sumathy , Christoforos Kanellakis , George Nikolakopoulos

We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a reward signal over time, while concurrently avoiding…

Machine Learning · Computer Science 2018-09-25 Tu-Hoa Pham , Giovanni De Magistris , Don Joven Agravante , Subhajit Chaudhury , Asim Munawar , Ryuki Tachibana

Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to…

Artificial Intelligence · Computer Science 2017-08-18 Felix Leibfried , Nate Kushman , Katja Hofmann

In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily…

Machine Learning · Computer Science 2024-05-31 Weiye Zhao , Feihan Li , Yifan Sun , Rui Chen , Tianhao Wei , Changliu Liu

Deploying deep reinforcement learning in safety-critical settings requires developing algorithms that obey hard constraints during exploration. This paper contributes a first approach toward enforcing formal safety constraints on end-to-end…

Artificial Intelligence · Computer Science 2020-07-03 Nathan Hunt , Nathan Fulton , Sara Magliacane , Nghia Hoang , Subhro Das , Armando Solar-Lezama

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Artificial Intelligence · Computer Science 2026-05-13 Xingyuan Hua , Sheng Yue , Ju Ren

In this work we consider partially observable environments with sparse rewards. We present a self-supervised representation learning method for image-based observations, which arranges embeddings respecting temporal distance of…

Machine Learning · Computer Science 2020-10-07 Aleksandr Ermolov , Nicu Sebe

Reinforcement Learning (RL) has been able to solve hard problems such as playing Atari games or solving the game of Go, with a unified approach. Yet modern deep RL approaches are still not widely used in real-world applications. One reason…

Machine Learning · Computer Science 2021-03-08 Achraf Azize , Othman Gaizi