AI Agent - arXivDaily 专题

2307.05834 2023-07-13 cs.LG cs.AI 62%

Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing

Sanae Amani, Khushbu Pahwa, Vladimir Braverman, Lin F. Yang

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

2307.05603 2023-07-13 cs.SE cs.LG cs.PL 62%

Can You Improve My Code? Optimizing Programs with Local Search

Fatemeh Abdollahi, Saqib Ameen, Matthew E. Taylor, Levi H. S. Lelis

专题命中软件智能体：agent(abstract)；分类 cs.LG、cs.SE

Comments International Joint Conference on Artificial Intelligence (IJCAI) 2023

2302.03921 2023-06-06 cs.LG cs.AI 62%

Predictable MDP Abstraction for Unsupervised Model-Based RL

Seohong Park, Sergey Levine

专题命中软件智能体：planning(abstract)；分类 cs.AI、cs.LG

Comments ICML 2023

2305.14343 2023-05-31 cs.LG cs.AI cs.CV 62%

Video Prediction Models as Rewards for Reinforcement Learning

Alejandro Escontrela, Ademi Adeniji, Wilson Yan, Ajay Jain, Xue Bin Peng, Ken Goldberg, Youngwoon Lee, Danijar Hafner, Pieter Abbeel

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments 22 pages, 18 figures, 4 tables. under review

2305.17052 2023-05-29 cs.LG cs.AI cs.CY cs.GT cs.MA 62%

A Framework for Incentivized Collaborative Learning

Xinran Wang, Qi Le, Ahmad Faraz Khan, Jie Ding, Ali Anwar

专题命中软件智能体：AI agent(abstract)；分类 cs.AI、cs.LG

2305.13738 2023-05-24 cs.CL cs.AI cs.CV 62%

i-Code Studio: A Configurable and Composable Framework for Integrative AI

Yuwei Fang, Mahmoud Khademi, Chenguang Zhu, Ziyi Yang, Reid Pryzant, Yichong Xu, Yao Qian, Takuya Yoshioka, Lu Yuan, Michael Zeng, Xuedong Huang

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.CL

2211.05732 2023-05-23 cs.GT cs.AI cs.LG econ.TH 62%

The Sample Complexity of Online Contract Design

Banghua Zhu, Stephen Bates, Zhuoran Yang, Yixin Wang, Jiantao Jiao, Michael I. Jordan

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

2205.14410 2023-04-28 cs.LG cs.AI 62%

Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning

Remo Sasso, Matthia Sabatelli, Marco A. Wiering

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments 24 pages, 7 figures, 8 tables. arXiv admin note: text overlap with arXiv:2108.06526

2303.05383 2023-03-10 cs.CL cs.CY cs.LG 62%

Making a Computational Attorney

Dell Zhang, Frank Schilder, Jack G. Conrad, Masoud Makrehchi, David von Rickenbach, Isabelle Moulinier

专题命中软件智能体：agent(abstract)；分类 cs.CL、cs.LG

Comments To be published in the Proceedings of the 2023 SIAM International Conference on Data Mining (SDM'23)

2206.06169 2023-03-09 cs.LG cs.AI stat.ML 62%

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems

Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M. Asano, Taco Cohen, Efstratios Gavves

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments Published at International Conference on Learning Representations (ICLR), 2023

2209.00588 2023-03-02 cs.LG cs.AI cs.CV 62%

Transformers are Sample-Efficient World Models

Vincent Micheli, Eloi Alonso, François Fleuret

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments ICLR 2023 (notable top 5%)

2302.08733 2023-02-20 cs.LG cs.AI 62%

Data Driven Reward Initialization for Preference based Reinforcement Learning

Mudit Verma, Subbarao Kambhampati

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments R2HCAI, AAAI 2023

2210.16530 2023-01-02 cs.LG cs.AI cs.RO 62%

BIMRL: Brain Inspired Meta Reinforcement Learning

Seyed Roozbeh Razavi Rohani, Saeed Hedayatian, Mahdieh Soleymani Baghshah

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted to 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

2212.09292 2022-12-20 cs.AI cs.CL 62%

ChatGPT: The End of Online Exam Integrity?

Teo Susnjak

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.CL

2211.14607 2022-11-29 cs.CV cs.AI cs.NE cs.SE 62%

Sketch2FullStack: Generating Skeleton Code of Full Stack Website and Application from Sketch using Deep Learning and Computer Vision

Somoy Subandhu Barua, Imam Mohammad Zulkarnain, Abhishek Roy, Md. Golam Rabiul Alam, Md Zia Uddin

专题命中软件智能体：workflow(abstract)；分类 cs.AI、cs.SE

Comments 12 pages, 10 figures, preprint

2211.08802 2022-11-17 cs.LG cs.AI stat.ML 62%

Giving Feedback on Interactive Student Programs with Meta-Exploration

Evan Zheran Liu, Moritz Stephan, Allen Nie, Chris Piech, Emma Brunskill, Chelsea Finn

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments Advances in Neural Information Processing Systems (NeurIPS 2022). Selected as Oral

2210.13555 2022-10-26 cs.LG cs.AI cs.SY eess.SY 62%

Energy Pricing in P2P Energy Systems Using Reinforcement Learning

Nicolas Avila, Shahad Hardan, Elnura Zhalieva, Moayad Aloqaily, Mohsen Guizani

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

2210.13269 2022-10-25 cs.CV cs.AI cs.LG 62%

IQUAFLOW: A new framework to measure image quality

P. Gallés, K. Takats, M. Hernández-Cabronero, D. Berga, L. Pega, L. Riordan-Chen, C. Garcia, G. Becker, A. Garriga, A. Bukva, J. Serra-Sagristà, D. Vilaseca, J. Marín

专题命中软件智能体：tool use(abstract)；分类 cs.AI、cs.LG

2205.15241 2022-10-18 cs.AI cs.LG 62%

Multi-Game Decision Transformers

Kuang-Huei Lee, Ofir Nachum, Mengjiao Yang, Lisa Lee, Daniel Freeman, Winnie Xu, Sergio Guadarrama, Ian Fischer, Eric Jang, Henryk Michalewski, Igor Mordatch

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2022. 24 pages, 16 figures. Additional information, videos and code can be seen at https://sites.google.com/view/multi-game-transformers

2209.15595 2022-10-03 cs.LG cs.AI 62%

Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks

Mahdi Morafah, Saeed Vahidian, Chen Chen, Mubarak Shah, Bill Lin

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments arXiv admin note: text overlap with arXiv:2209.10526

2110.09610 2022-09-14 cs.SE cs.LG 62%

A Survey on Machine Learning Techniques for Source Code Analysis

Tushar Sharma, Maria Kechagia, Stefanos Georgiou, Rohit Tiwari, Indira Vats, Hadi Moazen, Federica Sarro

专题命中软件智能体：workflow(abstract)；分类 cs.LG、cs.SE

2208.02821 2022-08-08 cs.LG cs.AI 62%

Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round

Manh Hung Nguyen, Lisheng Sun, Nathan Grinsztajn, Isabelle Guyon

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

2208.00003 2022-08-02 cs.LG cs.AI cs.GL cs.SY eess.SY math.OC 62%

RangL: A Reinforcement Learning Competition Platform

Viktor Zobernig, Richard A. Saldanha, Jinke He, Erica van der Sar, Jasper van Doorn, Jia-Chen Hua, Lachlan R. Mason, Aleksander Czechowski, Drago Indjic, Tomasz Kosmala, Alessandro Zocca, Sandjai Bhulai, Jorge Montalvo Arvizu, Claude Klöckl, John Moriarty

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments Documents in general and premierly the RangL competition plattform and in particular its 2022's competition "Pathways to Netzero" 10 pages, 2 figures, 1 table, Comments welcome!

2206.08888 2022-06-20 cs.LG cs.AI cs.NE 62%

Fast Population-Based Reinforcement Learning on a Single Machine

Arthur Flajolet, Claire Bizon Monroc, Karim Beguir, Thomas Pierrot

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

2101.03778 2022-05-24 cs.CL cs.LG 62%

Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection

Alexander Podolskiy, Dmitry Lipin, Andrey Bout, Ekaterina Artemova, Irina Piontkovskaya

专题命中软件智能体：agent(abstract)；分类 cs.CL、cs.LG

Comments AAAI 2021

2010.04466 2022-05-03 cs.LG cs.AI cs.NE q-bio.NC 62%

Learning Not to Learn: Nature versus Nurture in Silico

Robert Tjarko Lange, Henning Sprekeler

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

2204.12893 2022-04-28 cs.SE cs.AI 62%

Beyond Duplicates: Towards Understanding and Predicting Link Types in Issue Tracking Systems

Clara Marie Lüders, Abir Bouraffa, Walid Maalej

专题命中软件智能体：workflow(abstract)；分类 cs.AI、cs.SE

Comments 19th International Conference on Mining Software Repositories (MSR '22), May 23--24, 2022, Pittsburgh, PA, USA acmDOI: 10.1145/3524842.3528457

2204.04892 2022-04-12 cs.LG cs.AI 62%

JORLDY: a fully customizable open source framework for reinforcement learning

Kyushik Min, Hyunho Lee, Kwansu Shin, Taehak Lee, Hojoon Lee, Jinwon Choi, Sungho Son

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments 12 pages, 6 figures

2203.17251 2022-04-01 cs.CV cs.AI cs.LG cs.RO 62%

Continuous Scene Representations for Embodied AI

Samir Yitzhak Gadre, Kiana Ehsani, Shuran Song, Roozbeh Mottaghi

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments CVPR 2022

2203.11176 2022-03-22 cs.LG cs.AI cs.RO 62%

One After Another: Learning Incremental Skills for a Changing World

Nur Muhammad Shafiullah, Lerrel Pinto

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments To be published in The International Conference on Learning Representations (ICLR) 2022

1. 软件智能体 3217 篇

Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing

Can You Improve My Code? Optimizing Programs with Local Search

Predictable MDP Abstraction for Unsupervised Model-Based RL

Video Prediction Models as Rewards for Reinforcement Learning

A Framework for Incentivized Collaborative Learning

i-Code Studio: A Configurable and Composable Framework for Integrative AI

The Sample Complexity of Online Contract Design

Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning

Making a Computational Attorney

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems

Transformers are Sample-Efficient World Models

Data Driven Reward Initialization for Preference based Reinforcement Learning

BIMRL: Brain Inspired Meta Reinforcement Learning

ChatGPT: The End of Online Exam Integrity?

Sketch2FullStack: Generating Skeleton Code of Full Stack Website and Application from Sketch using Deep Learning and Computer Vision

Giving Feedback on Interactive Student Programs with Meta-Exploration

Energy Pricing in P2P Energy Systems Using Reinforcement Learning

IQUAFLOW: A new framework to measure image quality

Multi-Game Decision Transformers

Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks

A Survey on Machine Learning Techniques for Source Code Analysis

Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round

RangL: A Reinforcement Learning Competition Platform

Fast Population-Based Reinforcement Learning on a Single Machine

Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection

Learning Not to Learn: Nature versus Nurture in Silico

Beyond Duplicates: Towards Understanding and Predicting Link Types in Issue Tracking Systems

JORLDY: a fully customizable open source framework for reinforcement learning

Continuous Scene Representations for Embodied AI

One After Another: Learning Incremental Skills for a Changing World