Constrained decision transformer for offline safe reinforcement learning
Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the
environment. We aim to tackle a more challenging problem: learning a safe policy from an …
environment. We aim to tackle a more challenging problem: learning a safe policy from an …
Policycleanse: Backdoor detection and mitigation for competitive reinforcement learning
While real-world applications of reinforcement learning (RL) are becoming popular, the
security and robustness of RL systems are worthy of more attention and exploration. In …
security and robustness of RL systems are worthy of more attention and exploration. In …
Stealthy backdoor attack for code models
Code models, such as CodeBERT and CodeT5, offer general-purpose representations of
code and play a vital role in supporting downstream automated software engineering tasks …
code and play a vital role in supporting downstream automated software engineering tasks …
[HTML][HTML] A qualitative AI security risk assessment of autonomous vehicles
This paper systematically analyzes the security risks associated with artificial intelligence
(AI) components in autonomous vehicles (AVs). Given the increasing reliance on AI for …
(AI) components in autonomous vehicles (AVs). Given the increasing reliance on AI for …
What do users ask in open-source AI repositories? An empirical study of GitHub issues
Artificial Intelligence (AI) systems, which benefit from the availability of large-scale datasets
and increasing computational power, have become effective solutions to various critical …
and increasing computational power, have become effective solutions to various critical …
Badrl: Sparse targeted backdoor attack against reinforcement learning
Backdoor attacks in reinforcement learning (RL) have previously employed intense attack
strategies to ensure attack success. However, these methods suffer from high attack costs …
strategies to ensure attack success. However, these methods suffer from high attack costs …
Keep various trajectories: promoting exploration of ensemble policies in continuous control
The combination of deep reinforcement learning (DRL) with ensemble methods has been
proved to be highly effective in addressing complex sequential decision-making problems …
proved to be highly effective in addressing complex sequential decision-making problems …
Mutual Information as Intrinsic Reward of Reinforcement Learning Agents for On-demand Ride Pooling
The emergence of on-demand ride pooling services allows each vehicle to serve multiple
passengers at a time, thus increasing drivers' income and enabling passengers to travel at …
passengers at a time, thus increasing drivers' income and enabling passengers to travel at …
Pruning the Communication Bandwidth between Reinforcement Learning Agents through Causal Inference: An Innovative Approach to Designing a Smart Grid Power …
X Zhang, Y Liu, W Li, C Gong - Sensors, 2022 - mdpi.com
Electricity demands are increasing significantly and the traditional power grid system is
facing huge challenges. As the desired next-generation power grid system, smart grid can …
facing huge challenges. As the desired next-generation power grid system, smart grid can …
Manipulating Neural Path Planners via Slight Perturbations
Z Xiong, S Jagannathan - IEEE Robotics and Automation …, 2024 - ieeexplore.ieee.org
Data-driven neural path planners are attracting increasing interest in the robotics
community. However, their neural network components typically come as black boxes …
community. However, their neural network components typically come as black boxes …