Related papers: SafeRL-Lite: A Lightweight, Explainable, and Const…
Reinforcement learning (RL) is one of the most active fields of AI research. Despite the interest demonstrated by the research community in reinforcement learning, the development methodology still lags behind, with a severe lack of…
Increasing traffic demands, higher levels of automation, and communication enhancements provide novel design opportunities for future air traffic controllers (ATCs). This article presents a novel deep reinforcement learning (DRL) controller…
High-mix low-volume (HMLV) industrial assembly, common in small and medium-sized enterprises (SMEs), requires the same precision, safety, and reliability as high-volume automation while remaining flexible to product variation and…
We present \texttt{secml}, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion attacks to generate adversarial examples…
Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…
In many real-world applications, safety constraints for reinforcement learning (RL) algorithms are either unknown or not explicitly defined. We propose a framework that concurrently learns safety constraints and optimal RL policies in such…
Continual Reinforcement Learning (CRL) is a challenging setting where an agent learns to interact with an environment that is constantly changing over time (the stream of experiences). In this paper, we describe Avalanche RL, a library for…
Reinforcement learning (RL) is capable of sophisticated motion planning and control for robots in uncertain environments. However, state-of-the-art deep RL approaches typically lack safety guarantees, especially when the robot and…
We present Catalyst.RL, an open-source PyTorch framework for reproducible and sample efficient reinforcement learning (RL) research. Main features of Catalyst.RL include large-scale asynchronous distributed training, efficient…
Data preparation is a foundational yet notoriously challenging component of the machine learning lifecycle, characterized by a vast combinatorial search space. While reinforcement learning (RL) offers a promising direction, state-of-the-art…
The large-scale integration of intermittent renewable energy resources introduces increased uncertainty and volatility to the supply side of power systems, thereby complicating system operation and control. Recently, data-driven approaches,…
We tackle the challenge of training reliable code-fixing agents in real repositories, where complex builds and shifting dependencies make evaluation unstable. We developed a verifiable pipeline with success defined as post-fix build…
In this paper, we seek to learn a robot policy guaranteed to satisfy state constraints. To encourage constraint satisfaction, existing RL algorithms typically rely on Constrained Markov Decision Processes and discourage constraint…
Cyber-physical systems (CPS) require the joint optimization of discrete cyber actions and continuous physical parameters under stringent safety logic constraints. However, existing hierarchical approaches often compromise global optimality,…
We present NiceWebRL, a research tool that enables researchers to use machine reinforcement learning (RL) environments for online human subject experiments. NiceWebRL is a Python library that allows any Jax-based environment to be…
Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…
Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards,…
Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, but existing pipelines typically rely on per-task containers for isolation. At scale, pre-built container images incur substantial storage…
We present RLLTE: a long-term evolution, extremely modular, and open-source framework for reinforcement learning (RL) research and application. Beyond delivering top-notch algorithm implementations, RLLTE also serves as a toolkit for…
For all its successes, Reinforcement Learning (RL) still struggles to deliver formal guarantees on the closed-loop behavior of the learned policy. Among other things, guaranteeing the safety of RL with respect to safety-critical systems is…