AI Agent - arXivDaily 专题

2202.12622 2022-02-28 cs.AI 57%

Towards neoRL networks; the emergence of purposive graphs

Per R. Leikanger

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Submission to RLDM 2022

2202.08393 2022-02-18 cs.LG cs.RO 57%

Robust Reinforcement Learning via Genetic Curriculum

Yeeho Song, Jeff Schneider

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted to 2022 IEEE International Conference on Robotics and Automation (ICRA)

2106.00266 2022-02-18 cs.AI 57%

Did I do that? Blame as a means to identify controlled effects in reinforcement learning

Oriol Corcoll, Youssef Mohamed, Raul Vicente

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2112.04075 2022-02-10 cs.IT cs.LG math.IT 57%

Active Sensing for Communications by Learning

Foad Sohrabi, Tao Jiang, Wei Cui, Wei Yu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 14 Pages, 9 Figures; accepted in JSAC-SI-ISAC (IEEE Journal on Selected Areas in Communications Special Issue on Integrated Sensing and Communication). The source code for this paper is available at: https://github.com/foadsohrabi/DL-ActiveSensing

2202.02405 2022-02-09 cs.LG stat.ML 57%

BAM: Bayes with Adaptive Memory

Josue Nassar, Jennifer Brennan, Ben Evans, Kendall Lowrey

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments International Conference on Learning Representations (ICLR), 2022

2111.07958 2022-02-08 eess.SY cs.LG cs.SY 57%

Short-Term Power Prediction for Renewable Energy Using Hybrid Graph Convolutional Network and Long Short-Term Memory Approach

Wenlong Liao, Birgitte Bak-Jensen, Jayakrishnan Radhakrishna Pillai, Zhe Yang, Kuangpu Liu

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

Comments This paper was accepted the 22nd Power Systems Computation Conference (PSCC 2022)

2106.02951 2022-02-08 eess.SY cs.AI cs.SY 57%

Controller Synthesis for Omega-Regular and Steady-State Specifications

Alvaro Velasquez, Ismail Alkhouri, Andre Beckus, Ashutosh Trivedi, George Atia

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

2201.04480 2022-01-21 cs.LG cs.MA 57%

Learning to Identify Top Elo Ratings: A Dueling Bandits Approach

Xue Yan, Yali Du, Binxin Ru, Jun Wang, Haifeng Zhang, Xu Chen

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

2201.05299 2022-01-17 cs.CV cs.CL cs.IR 57%

A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering

Feng Gao, Qing Ping, Govind Thattai, Aishwarya Reganti, Ying Nian Wu, Prem Natarajan

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

2108.10876 2022-01-12 quant-ph cond-mat.stat-mech cs.AI cs.IT math.IT 57%

Quantum adaptive agents with efficient long-term memories

Thomas J. Elliott, Mile Gu, Andrew J. P. Garner, Jayne Thompson

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 16 pages, 4 figures

Journal ref Physical Review X 12, 011007 (2022)

2110.03473 2022-01-11 cs.CV cs.LG 57%

Unsupervised Image Decomposition with Phase-Correlation Networks

Angel Villar-Corrales, Sven Behnke

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

2010.07452 2022-01-11 math.OC cs.LG 57%

Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes

Ali Devran Kara, Serdar Yuksel

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

2005.11203 2022-01-03 cs.NE cs.AI q-bio.NC 57%

Towards a Neural Model for Serial Order in Frontal Cortex: a Brain Theory from Memory Development to Higher-Level Cognition

Alexandre Pitti, Mathias Quoy, Catherine Lavandier, Sofiane Boucenna, Wassim Swaileh, Claudio Weidmann

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

2112.10599 2021-12-21 cs.LG cs.CR math.PR 57%

Differentially Private Regret Minimization in Episodic Markov Decision Processes

Sayak Ray Chowdhury, Xingyu Zhou

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted by AAAI 2022

2112.09335 2021-12-20 cs.LG 57%

Community-based Layerwise Distributed Training of Graph Convolutional Networks

Hongyi Li, Junxiang Wang, Yongchao Wang, Yue Cheng, Liang Zhao

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments accepted by NeurIPS 2021 OPT workshop

2112.05575 2021-12-13 cs.AI cs.MA 57%

Paradigms of Computational Agency

Srinath Srinivasa, Jayati Deshmukh

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Earlier version of this paper was published as a book chapter in the book titled Novel Approaches to Information Systems Design

Journal ref In Novel Approaches to Information Systems Design, pp. 1-19. IGI Global, 2020

2112.04912 2021-12-10 cs.LG eess.SP stat.ML 57%

Scalable and Decentralized Algorithms for Anomaly Detection via Learning-Based Controlled Sensing

Geethu Joseph, Chen Zhong, M. Cenk Gursoy, Senem Velipasalar, Pramod K. Varshney

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 13 pages, 4 figures. arXiv admin note: substantial text overlap with arXiv:2105.06289

2112.04728 2021-12-10 cs.LG 57%

Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay

Hitesh Vaidya, Travis Desell, Alexander Ororbia

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2112.02843 2021-12-07 cs.RO cs.LG cs.MA 57%

Learning-based Measurement Scheduling for Loosely-Coupled Cooperative Localization

Jianan Zhu, Solmaz S. Kia

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 6 pages, 7 figures

2106.06317 2021-12-07 cs.LG 57%

Automatic Risk Adaptation in Distributional Reinforcement Learning

Frederik Schubert, Theresa Eimer, Bodo Rosenhahn, Marius Lindauer

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Journal ref Reinforcement Learning for Real Life Workshop, ICML 2021

2106.08849 2021-11-19 cs.LG 57%

How memory architecture affects learning in a simple POMDP: the two-hypothesis testing problem

Mario Geiger, Christophe Eloy, Matthieu Wyart

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2104.06890 2021-11-18 cs.AI 57%

An Introduction of mini-AlphaStar

Ruo-Ze Liu, Wenhai Wang, Yanjie Shen, Zhiqi Li, Yang Yu, Tong Lu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 11 pages, 2 figures

2111.08545 2021-11-17 cs.CL 57%

Coral: An Approach for Conversational Agents in Mental Health Applications

Harsh Sakhrani, Saloni Parekh, Shubham Mahajan

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments Accepted at the 5th Workshop on Widening Natural Language Processing at the Empirical Methods in Natural Language Processing Conference (EMNLP-WiNLP), 2021

2111.07876 2021-11-16 cs.AI 57%

Winning Solution of the AIcrowd SBB Flatland Challenge 2019-2020

Mugurel-Ionut Andreica

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Presented at the Flatland Challenge workshop at AMLD 2020 (https://appliedmldays.org/events/amld-epfl-2020/challenges/flatland-challenge)

2111.07125 2021-11-16 cs.LG cs.AR cs.RO eess.IV 57%

MC-CIM: Compute-in-Memory with Monte-Carlo Dropouts for Bayesian Edge Intelligence

Priyesh Shukla, Shamma Nasrin, Nastaran Darabi, Wilfred Gomes, Amit Ranjan Trivedi

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

2111.05527 2021-11-11 cs.AI 57%

LUMINOUS: Indoor Scene Generation for Embodied AI Challenges

Yizhou Zhao, Kaixiang Lin, Zhiwei Jia, Qiaozi Gao, Govind Thattai, Jesse Thomason, Gaurav S. Sukhatme

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

Comments 2021 paper, Amazon

2107.14702 2021-11-02 cs.GT cs.LG stat.ML 57%

Towards General Function Approximation in Zero-Sum Markov Games

Baihe Huang, Jason D. Lee, Zhaoran Wang, Zhuoran Yang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2008.00511 2021-11-02 cs.LG stat.ML 57%

Curriculum Learning with a Progression Function

Andrea Bassich, Francesco Foglino, Matteo Leonetti, Daniel Kudenko

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2010.11660 2021-11-01 cs.LG 57%

Detecting Rewards Deterioration in Episodic Reinforcement Learning

Ido Greenberg, Shie Mannor

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments ICML 2021

2110.15097 2021-10-29 cs.LG cs.IR 57%

Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning

Dusan Stamenkovic, Alexandros Karatzoglou, Ioannis Arapakis, Xin Xin, Kleomenis Katevas

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 9 pages, 4 figures, Proc. ACM WSDM, 2022 In Proceedings of the 15th ACM International Conference on Web Search and Data Mining (WSDM '22), February 21-25, 2022, Phoenix, Arizona

1. 记忆与上下文管理 4793 篇

Towards neoRL networks; the emergence of purposive graphs

Robust Reinforcement Learning via Genetic Curriculum

Did I do that? Blame as a means to identify controlled effects in reinforcement learning

Active Sensing for Communications by Learning

BAM: Bayes with Adaptive Memory

Short-Term Power Prediction for Renewable Energy Using Hybrid Graph Convolutional Network and Long Short-Term Memory Approach

Controller Synthesis for Omega-Regular and Steady-State Specifications

Learning to Identify Top Elo Ratings: A Dueling Bandits Approach

A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering

Quantum adaptive agents with efficient long-term memories

Unsupervised Image Decomposition with Phase-Correlation Networks

Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes

Towards a Neural Model for Serial Order in Frontal Cortex: a Brain Theory from Memory Development to Higher-Level Cognition

Differentially Private Regret Minimization in Episodic Markov Decision Processes

Community-based Layerwise Distributed Training of Graph Convolutional Networks

Paradigms of Computational Agency

Scalable and Decentralized Algorithms for Anomaly Detection via Learning-Based Controlled Sensing

Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay

Learning-based Measurement Scheduling for Loosely-Coupled Cooperative Localization

Automatic Risk Adaptation in Distributional Reinforcement Learning

How memory architecture affects learning in a simple POMDP: the two-hypothesis testing problem

An Introduction of mini-AlphaStar

Coral: An Approach for Conversational Agents in Mental Health Applications

Winning Solution of the AIcrowd SBB Flatland Challenge 2019-2020

MC-CIM: Compute-in-Memory with Monte-Carlo Dropouts for Bayesian Edge Intelligence

LUMINOUS: Indoor Scene Generation for Embodied AI Challenges

Towards General Function Approximation in Zero-Sum Markov Games

Curriculum Learning with a Progression Function

Detecting Rewards Deterioration in Episodic Reinforcement Learning

Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning