English
Related papers

Related papers: SEAR: Sample Efficient Action Chunking Reinforceme…

200 papers

Synchronizing expectations and knowledge about the state of the world is an essential capability for effective collaboration. For robots to effectively collaborate with humans and other autonomous agents, it is critical that they be able to…

Robotics · Computer Science 2021-01-07 Aaquib Tabrez , Ryan Leonard , Bradley Hayes

This paper introduces SOAR: Spilling with Orthogonality-Amplified Residuals, a novel data indexing technique for approximate nearest neighbor (ANN) search. SOAR extends upon previous approaches to ANN search, such as spill trees, that…

Machine Learning · Computer Science 2024-04-02 Philip Sun , David Simcha , Dave Dopson , Ruiqi Guo , Sanjiv Kumar

Online Network Resource Allocation (ONRA) for service provisioning is a fundamental problem in communication networks. As a sequential decision-making under uncertainty problem, it is promising to approach ONRA via Reinforcement Learning…

Networking and Internet Architecture · Computer Science 2021-10-19 Bahador Bakhshi , Josep Mangues-Bafalluy

Deep learning has achieved remarkable successes in solving challenging reinforcement learning (RL) problems when dense reward function is provided. However, in sparse reward environment it still often suffers from the need to carefully…

Machine Learning · Computer Science 2019-02-19 Hao Liu , Alexander Trott , Richard Socher , Caiming Xiong

Chunking is a crucial preprocessing step in retrieval-augmented generation (RAG) systems, significantly impacting retrieval effectiveness across diverse datasets. In this study, we systematically evaluate fixed-size chunking strategies and…

Information Retrieval · Computer Science 2025-05-30 Sinchana Ramakanth Bhat , Max Rudat , Jannis Spiekermann , Nicolas Flores-Herr

Recently developed offline reinforcement learning algorithms have made it possible to learn policies directly from pre-collected datasets, giving rise to a new dilemma for practitioners: Since the performance the algorithms are able to…

Machine Learning · Computer Science 2021-11-29 Phillip Swazinna , Steffen Udluft , Thomas Runkler

Feature selection and instance selection are two important techniques of data processing. However, such selections have mostly been studied separately, while existing work towards the joint selection conducts feature/instance selection…

Machine Learning · Computer Science 2022-05-18 Wei Fan , Kunpeng Liu , Hao Liu , Hengshu Zhu , Hui Xiong , Yanjie Fu

Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the…

Machine Learning · Computer Science 2018-09-10 Sameera Lanka , Tianfu Wu

Autoregressive networks can achieve promising performance in many sequence modeling tasks with short-range dependence. However, when handling high-dimensional inputs and outputs, the huge amount of parameters in the network lead to…

Machine Learning · Computer Science 2019-09-10 Di Wang , Feiqing Huang , Jingyu Zhao , Guodong Li , Guangjian Tian

Multi-stage ML inference pipelines are difficult to autoscale due to heterogeneous resources, cross-stage coupling, and dynamic bottleneck migration. We present SAIR, an autoscaling framework that uses an LLM as an in-context reinforcement…

Machine Learning · Computer Science 2026-02-02 Jianchang Su , Yifan Zhang , Shengkai Lin , Shizhen Zhao , Yusheng Zheng , Yiwei Yang , Wei Zhang

We introduce online action-stacking, an inference-time wrapper for reinforcement learning policies that produces realistic air traffic control commands while allowing training on a much smaller discrete action space. Policies are trained…

Machine Learning · Computer Science 2026-01-12 Ben Carvell , George De Ath , Eseoghene Benjamin , Richard Everson

Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep reinforcement learning. These agents are typically trained in cyber gym environments using dense, highly…

Machine Learning · Computer Science 2026-02-13 Elizabeth Bates , Chris Hicks , Vasilios Mavroudis

Humans are spectacular reinforcement learners, constantly learning from and adjusting to experience and feedback. Unfortunately, this doesn't necessarily mean humans are fast learners. When tasks are challenging, learning can become…

Machine Learning · Computer Science 2022-12-16 Mark A. Rucker , Layne T. Watson , Matthew S. Gerber , Laura E. Barnes

Retrieval-Augmented Generation (RAG) has emerged as a framework to address the constraints of Large Language Models (LLMs). Yet, its effectiveness fundamentally hinges on document chunking - an often-overlooked determinant of its quality.…

Information Retrieval · Computer Science 2026-03-26 Samuel Taiwo , Mohd Amaluddin Yusoff

In this paper, we propose a method to develop trustworthy reinforcement learning systems. To ensure safety especially during exploration, we automatically synthesize a correct-by-construction runtime enforcer, called a shield, that blocks…

Logic in Computer Science · Computer Science 2020-12-18 Bettina Könighofer , Julian Rudolf , Alexander Palmisano , Martin Tappler , Roderick Bloem

Scaling issues are mundane yet irritating for practitioners of reinforcement learning. Error scales vary across domains, tasks, and stages of learning; sometimes by many orders of magnitude. This can be detrimental to learning speed and…

Machine Learning · Computer Science 2021-05-13 Tom Schaul , Georg Ostrovski , Iurii Kemaev , Diana Borsa

Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically struggle with achieving effective exploration and are extremely sensitive to the choice of…

Machine Learning · Computer Science 2020-10-13 Shauharda Khadka , Somdeb Majumdar , Tarek Nassar , Zach Dwiel , Evren Tumer , Santiago Miret , Yinyin Liu , Kagan Tumer

Classic reinforcement learning (RL) frequently confronts challenges in tasks involving delays, which cause a mismatch between received observations and subsequent actions, thereby deviating from the Markov assumption. Existing methods…

Machine Learning · Computer Science 2024-06-06 Bo Xia , Yilun Kong , Yongzhe Chang , Bo Yuan , Zhiheng Li , Xueqian Wang , Bin Liang

Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectively minimize regret. However, recent advances in machine learning involve larger neural networks with…

Machine Learning · Computer Science 2024-12-20 Matthew Riemer , Gopeshh Subbaraj , Glen Berseth , Irina Rish

We study the problem of safe offline reinforcement learning (RL), the goal is to learn a policy that maximizes long-term reward while satisfying safety constraints given only offline data, without further interaction with the environment.…

Machine Learning · Computer Science 2022-04-11 Haoran Xu , Xianyuan Zhan , Xiangyu Zhu