AI Agent - arXivDaily 专题

2309.03710 2023-09-08 cs.LG 57%

A State Representation for Diminishing Rewards

Ted Moskovitz, Samo Hromadka, Ahmed Touati, Diana Borsa, Maneesh Sahani

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2309.02815 2023-09-07 cs.AI math.OC math.ST stat.TH 57%

Near-continuous time Reinforcement Learning for continuous state-action spaces

Lorenzo Croissant, Marc Abeille, Bruno Bouchard

专题命中记忆与上下文管理：planning(abstract)；分类 cs.AI

2302.09676 2023-09-06 cs.LG 57%

Leveraging Prior Knowledge in Reinforcement Learning via Double-Sided Bounds on the Value Function

Jacob Adamczyk, Stas Tiomkin, Rahul Kulkarni

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2303.15544 2023-08-30 cs.LG cs.NI 57%

Multi-Flow Transmission in Wireless Interference Networks: A Convergent Graph Learning Approach

Raz Paul, Kobi Cohen, Gil Kedar

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments This paper has been accepted for publication in the IEEE Transactions on Wireless Communications

2210.09107 2023-08-23 cs.LG cs.RO cs.SY eess.SY math.OC 57%

ISEE.U: Distributed online active target localization with unpredictable targets

Miguel Vasques, Claudia Soares, João Gomes

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2308.06498 2023-08-15 cs.AI cs.HC cs.RO 57%

Latent Emission-Augmented Perspective-Taking (LEAPT) for Human-Robot Interaction

Kaiqi Chen, Jing Yu Lim, Kingsley Kuan, Harold Soh

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2211.10515 2023-07-21 stat.ML cs.LG 57%

Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments

Daniel Jarrett, Corentin Tallec, Florent Altché, Thomas Mesnard, Rémi Munos, Michal Valko

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Journal ref In Proc. 40th International Conference on Machine Learning (ICML 2023)

2307.05629 2023-07-13 cs.AI cs.LO 57%

Characterization of AGM Belief Contraction in Terms of Conditionals

Giacomo Bonanno

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments In Proceedings TARK 2023, arXiv:2307.04005

Journal ref EPTCS 379, 2023, pp. 142-156

2306.16700 2023-07-03 cs.RO cs.CV cs.LG 57%

Dynamic-Resolution Model Learning for Object Pile Manipulation

Yixuan Wang, Yunzhu Li, Katherine Driggs-Campbell, Li Fei-Fei, Jiajun Wu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted to Robotics: Science and Systems (RSS) 2023. The first two authors contributed equally. Project Page: https://robopil.github.io/dyn-res-pile-manip

2306.12860 2023-06-23 cs.LG cs.CV 57%

Learning from Visual Observation via Offline Pretrained State-to-Go Transformer

Bohan Zhou, Ke Li, Jiechuan Jiang, Zongqing Lu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 19 pages

2109.08776 2023-06-23 cs.LG 57%

Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations

Ke Sun, Yingnan Zhao, Shangling Jui, Linglong Kong

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted in ECML PKDD 2023. This is the authors version of the work. The definitive Version of Record will be published in the Proceedings of ECML PKDD 2023

2306.09290 2023-06-16 cs.NI cs.LG 57%

Generalizable Resource Scaling of 5G Slices using Constrained Reinforcement Learning

Muhammad Sulaiman, Mahdieh Ahmadi, Mohammad A. Salahuddin, Raouf Boutaba, Aladdin Saleh

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2306.09211 2023-06-16 cs.LG cs.RO 57%

A Framework for Learning from Demonstration with Minimal Human Effort

Marc Rigter, Bruno Lacerda, Nick Hawes

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Preprint version of IEEE Robotics and Automation Letters paper

2211.08572 2023-06-16 cs.LG stat.ML 57%

Bayesian Fixed-Budget Best-Arm Identification

Alexia Atsidakou, Sumeet Katariya, Sujay Sanghavi, Branislav Kveton

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2306.05991 2023-06-12 cs.LG 57%

Approximate information state based convergence analysis of recurrent Q-learning

Erfan Seyedsalehi, Nima Akbarzadeh, Amit Sinha, Aditya Mahajan

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 25 pages, 6 figures

2306.03236 2023-06-07 cs.AI 57%

A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs

Mikael Henaff, Minqi Jiang, Roberta Raileanu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2306.00044 2023-06-02 cs.LG cs.CR cs.SD eess.AS 57%

How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning

Hye-jin Shim, Rosa González Hautamäki, Md Sahidullah, Tomi Kinnunen

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Interspeech 2023

2305.17109 2023-05-29 cs.LG 57%

Reinforcement Learning with Simple Sequence Priors

Tankred Saanum, Noémi Éltető, Peter Dayan, Marcel Binz, Eric Schulz

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2305.12233 2023-05-23 cs.CL 57%

A Measure of Explanatory Effectiveness

Dylan Cope, Peter McBurney

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments Presented at the 1st International Workshop on Trusted Automated Decision-Making (TADM) co-located with ETAPS 2021

2305.10681 2023-05-19 cs.LG cs.CR 57%

Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning

Yinglun Xu, Gagandeep Singh

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2305.09598 2023-05-17 cs.CL 57%

Boosting Event Extraction with Denoised Structure-to-Text Augmentation

bo wang, Heyan Huang, Xiaochi Wei, Ge Shi, Xiao Liu, Chong Feng, Tong Zhou, Shuaiqiang Wang, Dawei Yin

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments Findings of ACL 2023

2305.04477 2023-05-09 cs.LG 57%

Behavior Contrastive Learning for Unsupervised Skill Discovery

Rushuai Yang, Chenjia Bai, Hongyi Guo, Siyuan Li, Bin Zhao, Zhen Wang, Peng Liu, Xuelong Li

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted at the 40th International Conference on Machine Learning (ICML 2023)

2212.14177 2023-05-09 cs.AI cs.CY eess.IV 57%

Current State of Community-Driven Radiological AI Deployment in Medical Imaging

Vikash Gupta, Barbaros Selnur Erdal, Carolina Ramirez, Ralf Floca, Laurence Jackson, Brad Genereaux, Sidney Bryson, Christopher P Bridge, Jens Kleesiek, Felix Nensa, Rickmer Braren, Khaled Younis, Tobias Penzkofer, Andreas Michael Bucher, Ming Melvin Qin, Gigon Bae, Hyeonhoon Lee, M. Jorge Cardoso, Sebastien Ourselin, Eric Kerfoot, Rahul Choudhury, Richard D. White, Tessa Cook, David Bericat, Matthew Lungren, Risto Haukioja, Haris Shuaib

专题命中记忆与上下文管理：workflow(abstract)；分类 cs.AI

Comments 21 pages; 5 figures

2206.06719 2023-05-03 cs.LG 57%

Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning

Nicolas Castanet, Sylvain Lamprier, Olivier Sigaud

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2206.06426 2023-04-20 cs.LG stat.ML 57%

Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward

Tengyu Xu, Yue Wang, Shaofeng Zou, Yingbin Liang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Submitted for IEEE Transactions on Information Theory

2108.02998 2023-04-04 eess.IV cs.CV cs.LG physics.med-ph 57%

AI-based Aortic Vessel Tree Segmentation for Cardiovascular Diseases Treatment: Status Quo

Yuan Jin, Antonio Pepe, Jianning Li, Christina Gsaxner, Fen-hua Zhao, Kelsey L. Pomykala, Jens Kleesiek, Alejandro F. Frangi, Jan Egger

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2303.17878 2023-04-03 cs.LG 57%

Fused Depthwise Tiling for Memory Optimization in TinyML Deep Neural Network Inference

Rafael Stahl, Daniel Mueller-Gritschneder, Ulf Schlichtmann

专题命中记忆与上下文管理：planning(abstract)；分类 cs.LG

Comments Accepted as a full paper by the TinyML Research Symposium 2023

2301.00497 2023-04-03 cs.LG cs.SY eess.SY 57%

Efficient Online Learning with Memory via Frank-Wolfe Optimization: Algorithms with Bounded Dynamic Regret and Applications to Control

Hongyu Zhou, Zirui Xu, Vasileios Tzoumas

专题命中记忆与上下文管理：autonomous agent(abstract)；分类 cs.LG

Comments The version corrects proofs and updates presentation

2211.09702 2023-03-30 cs.NI cs.LG eess.SP 57%

Deep Reinforcement Learning Based Joint Downlink Beamforming and RIS Configuration in RIS-aided MU-MISO Systems Under Hardware Impairments and Imperfect CSI

Baturay Saglam, Doga Gurgunoglu, Suleyman S. Kozat

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 2023 IEEE International Conference on Communications Workshops (ICC Workshops)

2209.14390 2023-03-22 cs.LG cs.DC cs.MA 57%

Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data Distributions

Sai Aparna Aketi, Sangamesh Kodge, Kaushik Roy

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 29 pages, 5 figures, 16 tables. arXiv admin note: text overlap with arXiv:2103.02051 by other authors

1. 记忆与上下文管理 4758 篇

A State Representation for Diminishing Rewards

Near-continuous time Reinforcement Learning for continuous state-action spaces

Leveraging Prior Knowledge in Reinforcement Learning via Double-Sided Bounds on the Value Function

Multi-Flow Transmission in Wireless Interference Networks: A Convergent Graph Learning Approach

ISEE.U: Distributed online active target localization with unpredictable targets

Latent Emission-Augmented Perspective-Taking (LEAPT) for Human-Robot Interaction

Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments

Characterization of AGM Belief Contraction in Terms of Conditionals

Dynamic-Resolution Model Learning for Object Pile Manipulation

Learning from Visual Observation via Offline Pretrained State-to-Go Transformer

Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations

Generalizable Resource Scaling of 5G Slices using Constrained Reinforcement Learning

A Framework for Learning from Demonstration with Minimal Human Effort

Bayesian Fixed-Budget Best-Arm Identification

Approximate information state based convergence analysis of recurrent Q-learning

A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs

How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning

Reinforcement Learning with Simple Sequence Priors

A Measure of Explanatory Effectiveness

Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning

Boosting Event Extraction with Denoised Structure-to-Text Augmentation

Behavior Contrastive Learning for Unsupervised Skill Discovery

Current State of Community-Driven Radiological AI Deployment in Medical Imaging

Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning

Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward

AI-based Aortic Vessel Tree Segmentation for Cardiovascular Diseases Treatment: Status Quo

Fused Depthwise Tiling for Memory Optimization in TinyML Deep Neural Network Inference

Efficient Online Learning with Memory via Frank-Wolfe Optimization: Algorithms with Bounded Dynamic Regret and Applications to Control

Deep Reinforcement Learning Based Joint Downlink Beamforming and RIS Configuration in RIS-aided MU-MISO Systems Under Hardware Impairments and Imperfect CSI

Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data Distributions