相关论文: Guiding Safe Exploration with Weakest Precondition…

Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed, such as robust controllers or control barrier functions.…

Based on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performance (generalization) of PrLMs, or their robustness against…

The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…

This paper presents SPIE: a novel approach for semantic and structural post-training of instruction-based image editing diffusion models, addressing key challenges in alignment with user prompts and consistency with input images. We…

Traditional safety-critical control methods, such as control barrier functions, suffer from semantic blindness, exhibiting the same behavior around obstacles regardless of contextual significance. This limitation leads to the uniform…

Shielding is a popular technique for achieving safe reinforcement learning (RL). However, classical shielding approaches come with quite restrictive assumptions making them difficult to deploy in complex environments, particularly those…

We propose to leverage epistemic uncertainty about constraint satisfaction of a reinforcement learner in safety critical domains. We introduce a framework for specification of requirements for reinforcement learners in constrained settings,…

The working mechanisms of complex natural systems tend to abide by concise and profound partial differential equations (PDEs). Methods that directly mine equations from data are called PDE discovery, which reveals consistent physical laws…

This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty. Markov decision processes (MDPs) are prominent models to capture such planning problems. Reinforcement learning…

Reward-free reinforcement learning (RF-RL), a recently introduced RL paradigm, relies on random action-taking to explore the unknown environment without any reward feedback information. While the primary goal of the exploration phase in…

Influence maximization is the problem of finding a small subset of nodes in a network that can maximize the diffusion of information. Recently, it has also found application in HIV prevention, substance abuse prevention, micro-finance…

We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to learn. We propose a counter-intuitive solution that we call…

In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only offline data. Traditional methods often face difficulties in…

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to…

In this paper we propose a formal, model-agnostic meta-learning framework for safe reinforcement learning. Our framework is inspired by how parents safeguard their children across a progression of increasingly riskier tasks, imparting a…

Reinforcement learning (RL) agents need to explore their environments in order to learn optimal policies. In many environments and tasks, safety is of critical importance. The widespread use of simulators offers a number of advantages,…

The improved semantic understanding of vision-language pretrained (VLP) models has made it increasingly difficult to protect publicly posted images from being exploited by search engines and other similar tools. In this context, this paper…

Safe Reinforcement Learning (Safe RL) aims to train an RL agent to maximize its performance in real-world environments while adhering to safety constraints, as exceeding safety violation limits can result in severe consequences. In this…

While spatiotemporal deepfake detectors achieve high AUC, our experiments reveal their susceptibility to evasion attacks. These models tend to overfit on fragile temporal spectrum cues, rather than learning robust semantic causality. To…

A longstanding goal in safe reinforcement learning (RL) is a method to ensure the safety of a policy throughout the entire process, from learning to operation. However, existing safe RL paradigms inherently struggle to achieve this…