Related papers: SafePILCO: a software tool for safe and data-effic…
Ensuring safety is important for the practical deployment of reinforcement learning (RL). Various challenges must be addressed, such as handling stochasticity in the environments, providing rigorous guarantees of persistent state-wise…
Software security incidents occur everyday and thousands of software security reports are announced each month. Thus, it is difficult for software security researchers, engineers, and other stakeholders to follow software security topics of…
The library scikit-fda is a Python package for Functional Data Analysis (FDA). It provides a comprehensive set of tools for representation, preprocessing, and exploratory analysis of functional data. The library is built upon and integrated…
In recent years, significant progress has been made in the field of robotic reinforcement learning (RL), enabling methods that handle complex image observations, train in the real world, and incorporate auxiliary data, such as…
Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy rollout-based safety constraints that can be evaluated…
In this paper, we present an early software integrating Reinforcement Learning (RL) with Model Predictive Control (MPC). Our aim is to make recent theoretical contributions from the literature more accessible to both the RL and MPC…
A MATLAB toolbox is presented, with the goal of checking occurrences of design errors typically found in fixed-point digital systems, considering finite word-length effects. In particular, the present toolbox works as a front-end to a…
Due to the long runtime of Data Science (DS) pipelines, even small programming mistakes can be very costly, if they are not detected statically. However, even basic static type checking of DS pipelines is difficult because most are written…
Speech synthesis technology has brought great convenience, while the widespread usage of realistic deepfake audio has triggered hazards. Malicious adversaries may unauthorizedly collect victims' speeches and clone a similar voice for…
Static analysis remains one of the most popular approaches for detecting and correcting poor or vulnerable program code. It involves the examination of code listings, test results, or other documentation to identify errors, violations of…
Safe reinforcement learning (RL) offers advanced solutions to constrained optimal control problems. Existing studies in safe RL implicitly assume continuity in policy functions, where policies map states to actions in a smooth,…
Modern cyber-physical systems are operated by complex software that increasingly takes over safety-critical functions. Software enables rapid iterations and continuous delivery of new functionality that meets the ever-changing expectations…
Just like the scientific data they generate, simulation workflows for research should be findable, accessible, interoperable, and reusable (FAIR). However, while significant progress has been made towards FAIR data, the majority of science…
Scientific workflow management systems offer features for composing complex computational pipelines from modular building blocks, for executing the resulting automated workflows, and for recording the provenance of data products resulting…
AsaPy is a custom-made Python library designed to simplify and optimize the analysis of aerospace simulation data. Instead of introducing new methodologies, it excels in combining various established techniques, creating a unified,…
Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…
Guaranteeing safety in human-centric applications is critical in robot learning as the learned policies may demonstrate unsafe behaviors in formerly unseen scenarios. We present a framework to locally repair an erroneous policy network to…
Batch Reinforcement Learning (Batch RL) consists in training a policy using trajectories collected with another policy, called the behavioural policy. Safe policy improvement (SPI) provides guarantees with high probability that the trained…
You have an environment, a model, and a reinforcement learning library that are designed to work together but don't. PufferLib makes them play nice. The library provides one-line environment wrappers that eliminate common compatibility…
Flow-sensitive type systems offer an elegant way to ensure memory-safety in programming languages. Unfortunately, their adoption in new or existing languages is often hindered by a painful effort to implement or integrate them into…