AI Agent - arXivDaily 专题

2204.12371 2023-02-17 cs.LG cs.NE cs.SI 57%

Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning

Seungwoong Ha, Hawoong Jeong

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Main manuscript : 11 pages, 6 figures. Supplementary information : 7 pages, 7 figures

2103.07780 2023-02-16 cs.AI cs.GT 57%

Online Double Oracle

Le Cong Dinh, Yaodong Yang, Stephen McAleer, Zheng Tian, Nicolas Perez Nieves, Oliver Slumbers, David Henry Mguni, Haitham Bou Ammar, Jun Wang

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments Accepted at Transactions on Machine Learning Research (TMLR)

Journal ref Transactions on Machine Learning Research 2022

2207.05081 2023-02-15 cs.NE cs.LG q-bio.NC 57%

A Macrocolumn Architecture Implemented with Spiking Neurons

James E. Smith

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments This is a major revision. Neuron outputs are encoded as the body potential. Winner-take-all inhibition then compares body potentials to determine a winner. At the end of each cycle, a non-zero WTA output is converted to a binary spike. This method remains consistent with temporal neuron operation internal to a cycle, with only a single bit of temporal precision being maintained between cycles

2302.06557 2023-02-14 cs.LG 57%

Transient Hemodynamics Prediction Using an Efficient Octree-Based Deep Learning Model

Noah Maul, Katharina Zinn, Fabian Wagner, Mareike Thies, Maximilian Rohleder, Laura Pfaff, Markus Kowarschik, Annette Birkhold, Andreas Maier

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 13 pages, 5 figures

2302.03288 2023-02-08 cs.RO cs.AI 57%

Object-Centric Scene Representations using Active Inference

Toon Van de Maele, Tim Verbelen, Pietro Mazzaglia, Stefano Ferraro, Bart Dhoedt

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2103.10003 2023-02-08 eess.IV cs.CV cs.LG 57%

COVIDx-US -- An open-access benchmark dataset of ultrasound imaging data for AI-driven COVID-19 analytics

Ashkan Ebadi, Pengcheng Xi, Alexander MacLean, Stéphane Tremblay, Sonny Kohli, Alexander Wong

专题命中 Agent评测：planning(abstract)；分类 cs.LG

Comments 12 pages, 5 figures, to be submitted to Nature Scientific Data

Journal ref Front. Biosci. (Landmark Ed) 2022, 27(7), 198

2302.02788 2023-02-07 cs.LG 57%

A Strong Baseline for Batch Imitation Learning

Matthew Smith, Lucas Maystre, Zhenwen Dai, Kamil Ciosek

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 28 pages (10 main, 18 appendix), 4 figures

2201.11783 2023-02-07 cs.LG 57%

Boosting Exploration in Multi-Task Reinforcement Learning using Adversarial Networks

Ramnath Kumar, Tristan Deleu, Yoshua Bengio

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2111.04850 2023-02-07 cs.LG 57%

Dueling RL: Reinforcement Learning with Trajectory Preferences

Aldo Pacchiano, Aadirupa Saha, Jonathan Lee

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Aadirupa Saha and Aldo Pacchiano contributed equally

2210.15096 2023-02-02 cs.AI 57%

Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion

Utkarsh Soni, Nupur Thakur, Sarath Sreedharan, Lin Guan, Mudit Verma, Matthew Marquez, Subbarao Kambhampati

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2208.08110 2023-02-01 cs.CL 57%

PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation

Hongyuan Lu, Wai Lam

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments Accepted to EACL 2023 (main)

1907.03809 2023-02-01 econ.TH cs.LG econ.EM 57%

Competing Models

Jose Luis Montiel Olea, Pietro Ortoleva, Mallesh M Pai, Andrea Prat

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2301.13136 2023-01-31 cs.LG 57%

Contrastive Meta-Learning for Partially Observable Few-Shot Learning

Adam Jelley, Amos Storkey, Antreas Antoniou, Sam Devlin

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Accepted for publication at ICLR 2023. Code is available at https://github.com/AdamJelley/POEM

2205.09683 2023-01-31 cs.RO cs.LG 57%

Dexterous Robotic Manipulation using Deep Reinforcement Learning and Knowledge Transfer for Complex Sparse Reward-based Tasks

Qiang Wang, Francisco Roldan Sanchez, Robert McCarthy, David Cordova Bulens, Kevin McGuinness, Noel O'Connor, Manuel Wüthrich, Felix Widmaier, Stefan Bauer, Stephen J. Redmond

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments This paper has been summited to Expert Systems: the Journal of Knowledge Engineering for reviewing. arXiv admin note: text overlap with arXiv:2109.15233

1912.01683 2023-01-31 cs.AI 57%

Optimal Policies Tend to Seek Power

Alexander Matt Turner, Logan Smith, Rohin Shah, Andrew Critch, Prasad Tadepalli

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments Accepted to NeurIPS 2021 as spotlight paper. 12 pages, 44 pages with appendices. Since the 2021 acceptance, we updated the paper to point out that optimal policies can be qualitatively divorced from real-world learned policies

2110.13400 2023-01-27 cs.LG stat.ML 57%

Scale-Free Adversarial Multi-Armed Bandit with Arbitrary Feedback Delays

Jiatai Huang, Yan Dai, Longbo Huang

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Preliminary work, merged to arXiv:2301.10500

2301.10077 2023-01-26 cs.LG hep-th 57%

Autonomous particles

Nikola Andrejic, Vitaly Vanchurin

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 15 pages, 3 figures

2301.08632 2023-01-25 cs.IR cs.LG 57%

Generative Slate Recommendation with Reinforcement Learning

Romain Deffayet, Thibaut Thonet, Jean-Michel Renders, Maarten de Rijke

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments WSDM 2023, 9 pages, 3 figures

2205.03787 2023-01-24 eess.SY cs.LG cs.SY 57%

Learning Regionally Decentralized AC Optimal Power Flows with ADMM

Terrence W. K. Mak, Minas Chatzos, Mathieu Tanneau, Pascal Van Hentenryck

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 14 pages

2109.08856 2023-01-24 cs.GT cs.AI 57%

Favoring Eagerness for Remaining Items: Designing Efficient, Fair, and Strategyproof Mechanisms

Xiaoxi Guo, Sujoy Sikdar, Lirong Xia, Yongzhi Cao, Hanpin Wang

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Journal ref Journal of Artificial Intelligence Research 76 (2023) 287-339

2207.13398 2023-01-23 cs.AI cs.HC 57%

Emergent social NPC interactions in the Social NPCs Skyrim mod and beyond

Manuel Guimarães, Pedro A. Santos, Arnav Jhala

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments Originally a chapter for Game AI Pro, contains 14 pages, 3 figures

2301.07768 2023-01-20 eess.SY cs.LG cs.SY 57%

Automated deep reinforcement learning for real-time scheduling strategy of multi-energy system integrated with post-carbon and direct-air carbon captured system

Tobi Michael Alabi, Nathan P. Lawrence, Lin Lu, Zaiyue Yang, R. Bhushan Gopaluni

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 39 pages; postprint

Journal ref Applied Energy, Volume 333, 1 March 2023, 120633

2210.11692 2023-01-16 cs.LG cs.GT cs.MA 57%

Competing Bandits in Time Varying Matching Markets

Deepan Muthirayan, Chinmay Maheshwari, Pramod P. Khargonekar, Shankar Sastry

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2301.03887 2023-01-11 cs.LG 57%

Actor-Director-Critic: A Novel Deep Reinforcement Learning Framework

Zongwei Liu, Yonghong Song, Yuanlin Zhang

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2301.03771 2023-01-11 cs.CR cs.CY cs.LG 57%

Chatbots in a Honeypot World

Forrest McKee, David Noever

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2208.14037 2023-01-10 cs.AI 57%

Towards Artificial Virtuous Agents: Games, Dilemmas and Machine Learning

Ajay Vishwanath, Einar Duenger Bøhn, Ole-Christoffer Granmo, Charl Maree, Christian Omlin

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments Premature submission of revised revision

2003.05162 2023-01-10 cs.CV cs.CL 57%

Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning

Zhiyuan Fang, Tejas Gokhale, Pratyay Banerjee, Chitta Baral, Yezhou Yang

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments EMNLP 2020. V2C Website: https://asu-apg.github.io/Video2Commonsense/

2210.01723 2023-01-09 cs.CV cs.AI 57%

Dense Prediction Transformer for Scale Estimation in Monocular Visual Odometry

André O. Françani, Marcos R. O. A. Maximo

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2301.00005 2023-01-05 cs.AI physics.app-ph 57%

Intrinsic Motivation in Dynamical Control Systems

Stas Tiomkin, Ilya Nemenman, Daniel Polani, Naftali Tishby

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2301.01474 2023-01-05 eess.SY cs.LG cs.SY 57%

UAV aided Metaverse over Wireless Communications: A Reinforcement Learning Approach

Peiyuan Si, Wenhan Yu, Jun Zhao, Kwok-Yan Lam, Qing Yang

专题命中 Agent评测：agent(abstract)；分类 cs.LG

1. Agent评测 15866 篇

Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning

Online Double Oracle

A Macrocolumn Architecture Implemented with Spiking Neurons

Transient Hemodynamics Prediction Using an Efficient Octree-Based Deep Learning Model

Object-Centric Scene Representations using Active Inference

COVIDx-US -- An open-access benchmark dataset of ultrasound imaging data for AI-driven COVID-19 analytics

A Strong Baseline for Batch Imitation Learning

Boosting Exploration in Multi-Task Reinforcement Learning using Adversarial Networks

Dueling RL: Reinforcement Learning with Trajectory Preferences

Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion

PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation

Competing Models

Contrastive Meta-Learning for Partially Observable Few-Shot Learning

Dexterous Robotic Manipulation using Deep Reinforcement Learning and Knowledge Transfer for Complex Sparse Reward-based Tasks

Optimal Policies Tend to Seek Power

Scale-Free Adversarial Multi-Armed Bandit with Arbitrary Feedback Delays

Autonomous particles

Generative Slate Recommendation with Reinforcement Learning

Learning Regionally Decentralized AC Optimal Power Flows with ADMM

Favoring Eagerness for Remaining Items: Designing Efficient, Fair, and Strategyproof Mechanisms

Emergent social NPC interactions in the Social NPCs Skyrim mod and beyond

Automated deep reinforcement learning for real-time scheduling strategy of multi-energy system integrated with post-carbon and direct-air carbon captured system

Competing Bandits in Time Varying Matching Markets

Actor-Director-Critic: A Novel Deep Reinforcement Learning Framework

Chatbots in a Honeypot World

Towards Artificial Virtuous Agents: Games, Dilemmas and Machine Learning

Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning

Dense Prediction Transformer for Scale Estimation in Monocular Visual Odometry

Intrinsic Motivation in Dynamical Control Systems

UAV aided Metaverse over Wireless Communications: A Reinforcement Learning Approach