Related papers: SWE-MiniSandbox: Container-Free Reinforcement Lear…

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for training large language models (LLMs) on complex reasoning tasks, such as mathematical problem solving. A prerequisite for the scalability of RLVR is a…

With the rapid growth of IoT devices and their diverse workloads, container-based microservices deployed at edge nodes have become a lightweight and scalable solution. However, existing microservice scheduling algorithms often assume static…

Motivated by recent advancements in Deep Reinforcement Learning (RL), we have developed an RL agent to manage the operation of storage devices in a household and is designed to maximize demand-side cost savings. The proposed technique is…

Rehearsal is a critical component for class-incremental continual learning, yet it requires a substantial memory budget. Our work investigates whether we can significantly reduce this memory budget by leveraging unlabeled data from an…

Recent advances in off-policy deep reinforcement learning (RL) have led to impressive success in complex tasks from visual observations. Experience replay improves sample-efficiency by reusing experiences from the past, and convolutional…

Small LLMs often struggle to match the agentic capabilities of large, costly models. While reinforcement learning can help, progress has been limited by two structural bottlenecks: existing open-source agentic training data are narrow in…

Chain-of-thought reasoning in large language models can trigger an "overthinking trap": longer rollouts raise cost and latency yet often yield unreliable accuracy gains. Existing methods use global, static controls that may suppress needed…

Robotic manipulation in cluttered environments presents a critical challenge for automation. Recent large-scale, end-to-end models demonstrate impressive capabilities but often lack the data efficiency and modularity required for retrieving…

Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…

Image classification technology and performance based on Deep Learning have already achieved high standards. Nevertheless, many efforts have conducted to improve the stability of classification via ensembling. However, the existing ensemble…

Software sandboxing or software-based fault isolation (SFI) is a lightweight approach to building secure systems out of untrusted components. Mozilla, for example, uses SFI to harden the Firefox browser by sandboxing third-party libraries,…

As the number of spacecraft in orbit continues to increase, it is becoming more challenging for human operators to manage each mission. As a result, autonomous control methods are needed to reduce this burden on operators. One method of…

The promotion of large-scale applications of reinforcement learning (RL) requires efficient training computation. While existing parallel RL frameworks encompass a variety of RL algorithms and parallelization techniques, the excessively…

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…

This paper presents a comprehensive benchmarking suite tailored to offline safe reinforcement learning (RL) challenges, aiming to foster progress in the development and evaluation of safe learning algorithms in both the training and…

Reinforcement learning (RL) has gained traction for its success in solving complex tasks for robotic applications. However, its deployment on physical robots remains challenging due to safety risks and the comparatively high costs of…

Articulated object manipulation is a challenging task, requiring constrained motion and adaptive control to handle the unknown dynamics of the manipulated objects. While reinforcement learning (RL) has been widely employed to tackle various…

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

Reinforcement learning (RL) is an appealing paradigm for training intelligent agents, enabling policy acquisition from the agent's own autonomously acquired experience. However, the training process of RL is far from automatic, requiring…

We introduce OpenTinker, an infrastructure for reinforcement learning (RL) of large language model (LLM) agents built around a separation of concerns across algorithm design, execution, and agent-environment interaction. Rather than relying…