Related papers: Adaptive Data Exploitation in Deep Reinforcement L…
Inverse Reinforcement Learning (IRL) learns an optimal policy, given some expert demonstrations, thus avoiding the need for the tedious process of specifying a suitable reward function. However, current methods are constrained by at least…
Data acquisition efficiency is a central challenge in deploying reinforcement learning in business and healthcare operations, where interactions are costly, slow, and often involve humans in the loop. This paper develops a unified large…
We introduce a reinforcement learning (RL) based adaptive optimization algorithm for aerodynamic shape optimization focused on dimensionality reduction. The form in which RL is applied here is that of a surrogate-based, actor-critic policy…
In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. Existing AutoGPT-style techniques have inherent limitations, such as a heavy reliance on precise descriptions for…
Large language models (LLMs) have shown great potential in code-related tasks, yet open-source models lag behind their closed-source counterparts. To bridge this performance gap, existing methods generate vast amounts of synthetic data for…
Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause…
Extensive research demonstrates that Deep Reinforcement Learning (DRL) models are susceptible to adversarially constructed inputs (i.e., adversarial examples), which can mislead the agent to take suboptimal or unsafe actions. Recent methods…
Sample inefficiency is a long-lasting challenge in deep reinforcement learning (DRL). Despite dramatic improvements have been made, the problem is far from being solved and is especially challenging in environments with sparse or delayed…
The era of huge data necessitates highly efficient machine learning algorithms. Many common machine learning algorithms, however, rely on computationally intensive subroutines that are prohibitively expensive on large datasets. Oftentimes,…
One practical challenge in reinforcement learning (RL) is how to make quick adaptations when faced with new environments. In this paper, we propose a principled framework for adaptive RL, called \textit{AdaRL}, that adapts reliably and…
Modern scientific data acquisition generates petabytes of data that must be transferred to geographically distant computing clusters. Conventional tools either rely on preconfigured sessions, which are difficult to tune for users without…
Action-constrained reinforcement learning (ACRL) is a generic framework for learning control policies with zero action constraint violation, which is required by various safety-critical and resource-constrained applications. The existing…
To utilize pre-trained neural networks on edge and mobile devices, we often require efficient adaptation to user-specific runtime data distributions while operating under limited compute and memory resources. On-device retraining with a…
In recent years, reinforcement learning and bandits have transformed a wide range of real-world applications including healthcare, finance, recommendation systems, robotics, and last but not least, the speech and natural language…
The growing demand for optimal and low-power energy consumption paradigms for IOT devices has garnered significant attention due to their cost-effectiveness, simplicity, and intelligibility. In this article, an AI hardware energy-efficient…
Visual instruction datasets from various distributors are released at different times and often contain a significant number of semantically redundant text-image pairs, depending on their task compositions (i.e., skills) or reference…
We propose a reinforcement learning (RL) framework for adaptive precision tuning for linear solvers, which can be extended to general algorithms. The framework is formulated as a contextual bandit problem and solved using incremental…
This paper presents AdaptEx, a self-service contextual bandit platform widely used at Expedia Group, that leverages multi-armed bandit algorithms to personalize user experiences at scale. AdaptEx considers the unique context of each visitor…
Divisible Load Theory (DLT) is a powerful tool for modeling divisible load problems in data-intensive systems. This paper studied an optimal divisible load distribution sequencing problem using a machine learning framework. The problem is…
Prompt Tuning (PT) enables the adaptation of Pre-trained Large Language Models (PLMs) to downstream tasks by optimizing a small amount of soft virtual tokens, which are prepended to the input token embeddings. Recently, Decomposed Prompt…