Related papers: A Deep Recurrent-Reinforcement Learning Method for…

Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with primary challenges being concept drift and the high cost of gradient-based adaptation.…

Real-time learning is crucial for robotic agents adapting to ever-changing, non-stationary environments. A common setup for a robotic agent is to have two different computers simultaneously: a resource-limited local computer tethered to the…

Safety is the priority concern when applying reinforcement learning (RL) algorithms to real-world control problems. While policy iteration provides a fundamental algorithm for standard RL, an analogous theoretical algorithm for safe RL…

Function-as-a-Service (FaaS) platforms and "serverless" cloud computing are becoming increasingly popular. Current FaaS offerings are targeted at stateless functions that do minimal I/O and communication. We argue that the benefits of…

As Large Language Models (LLMs) become ubiquitous across various scientific domains, their lack of ability to perform complex tasks like running simulations or to make complex decisions limits their utility. LLM-based agents bridge this gap…

Modern FaaS systems perform well in the case of repeat executions when function working sets stay small. However, these platforms are less effective when applied to more complex, large-scale and dynamic workloads. In this paper, we…

Cloud computing has established itself as the support for the vast majority of emerging technologies, mainly due to the characteristic of elasticity it offers. Auto-scalers are the systems that enable this elasticity by acquiring and…

Function-as-a-Service (FaaS) is a type of serverless computing that allows developers to write and deploy code as individual functions, which can be triggered by specific events or requests. FaaS platforms automatically manage the…

This paper proposes an automated framework for efficient application profiling and training of Machine Learning (ML) performance models, composed of two parts: OSCAR-P and aMLLibrary. OSCAR-P is an auto-profiling tool designed to…

Serverless computing has achieved widespread adoption, with over 70% of AWS organizations using serverless solutions [1]. Meanwhile, machine learning inference workloads increasingly migrate to Function-as-a-Service (FaaS) platforms for…

We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially observable environments. Predictive state policy…

Serverless computing promises convenient abstractions for developing and deploying functions that execute in response to events. In such Function-as-a-Service (FaaS) platforms, scheduling is an integral task, but current scheduling…

Large language models (LLMs) excel in tasks like question answering and dialogue, but complex tasks requiring interaction, such as negotiation and persuasion, require additional long-horizon reasoning and planning. Reinforcement learning…

Function as a Service (FaaS) paradigm is becoming widespread and is envisioned as the next generation of cloud systems that mitigate the burden for programmers and cloud solution architects. However, the FaaS abstraction only makes the…

AI for IT Operations (AIOps) aims to automate complex operational tasks, such as fault localization and root cause analysis, to reduce human workload and minimize customer impact. While traditional DevOps tools and AIOps algorithms often…

Serverless computing has redefined cloud application deployment by abstracting infrastructure and enabling on-demand, event-driven execution, thereby enhancing developer agility and scalability. However, maintaining consistent application…

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely used for their stability, but their reliance on narrowly…

Plateaus, where an agent's performance stagnates at a suboptimal level, are a common problem in deep on-policy RL. Focusing on PPO due to its widespread adoption, we show that plateaus in certain regimes arise not because of known…

Reinforcement Learning (RL) has emerged as the key driver for post-training complex reasoning in Large Language Models (LLMs), yet online RL introduces significant instability and computational overhead. Offline RL offers a compelling…