Related papers: Re-incentivizing Discovery: Mechanisms for Partial…
Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to…
Collaboration among researchers is an essential component of the modern scientific enterprise, playing a particularly important role in multidisciplinary research. However, we continue to wrestle with allocating credit to the coauthors of…
Science and technology journalists today face challenges in finding newsworthy leads due to increased workloads, reduced resources, and expanding scientific publishing ecosystems. Given this context, we explore computational methods to aid…
Participation incentives is a well-known issue inhibiting randomized controlled trials (RCTs) in medicine, as well as a potential cause of user dissatisfaction for RCTs in online platforms. We frame this issue as a non-standard…
We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives---policies that are executed for large numbers of timesteps. Specifically,…
In decentralized stochastic control, standard approaches for sequential decision-making, e.g. dynamic programming, quickly become intractable due to the need to maintain a complex information state. Computational challenges are further…
Self-supervised methods have become crucial for advancing deep learning by leveraging data itself to reduce the need for expensive annotations. However, the question of how to conduct self-supervised offline reinforcement learning (RL) in a…
This paper explores an intrinsic motivation for mutual awareness, hypothesizing that humans possess a fundamental drive to understand and to be understood even in the absence of extrinsic rewards. Through simulations of the perceptual…
In this paper, we propose the first fully push-forward-based distributional reinforcement learning algorithm, named PACER, which consists of a distributional critic, a stochastic actor and a sample-based encourager. Specifically, the…
Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and…
Data sharing by researchers is a centerpiece of Open Science principles and scientific progress. For a sample of 6019 researchers, we analyze the extent/frequency of their data sharing. Specifically, the relationship with the following four…
Modern data marketplaces and data sharing consortia increasingly rely on incentive mechanisms to encourage agents to contribute data. However, schemes that reward agents based on the quantity of submitted data are vulnerable to…
Peer review is a key component of the publishing process in most fields of science. The increasing submission rates put a strain on reviewing quality and efficiency, motivating the development of applications to support the reviewing and…
Multi-task learning is an open and challenging problem in computer vision. The typical way of conducting multi-task learning with deep neural networks is either through handcrafted schemes that share all initial layers and branch out at an…
Scientific workflows are powerful tools for management of scalable experiments, often composed of complex tasks running on distributed resources. Existing cyberinfrastructure provides components that can be utilized within repeatable…
Self-organizing systems consist of autonomous agents that can perform complex tasks and adapt to dynamic environments without a central controller. Prior research often relies on reinforcement learning to enable agents to gain the skills…
Beyond sharing datasets or simulations, we believe the Recommender Systems (RS) community should share Task Environments. In this work, we propose a high-level logical architecture that will help to reason about the core components of a RS…
Providing proper economic incentives is essential for the success of dynamic spectrum sharing. Cooperative spectrum sharing is one effective way to achieve this goal. In cooperative spectrum sharing, secondary users (SUs) relay traffics for…
Traditional regulatory methods for spectrum licensing have been recently identified as one of the causes for the under-utilization of the valuable radio spectrum. Governmental agencies such as the Federal Communications Commission (FCC) are…
Cooperation is fundamental in Multi-Agent Systems (MAS) and Multi-Agent Reinforcement Learning (MARL), often requiring agents to balance individual gains with collective rewards. In this regard, this paper aims to investigate strategies to…