AI Agent - arXivDaily 专题

2308.15911 2023-08-31 cs.LG cs.AI cs.RO 62%

Cyclophobic Reinforcement Learning

Stefan Sylvius Wagner, Peter Arndt, Jan Robine, Stefan Harmeling

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Published in Transactions on Machine Learning Research (08/2023)

2305.07500 2023-08-14 cs.LG cs.AI 62%

Learning representations that are closed-form Monge mapping optimal with application to domain adaptation

Oliver Struckmeier, Ievgen Redko, Anton Mallasto, Karol Arndt, Markus Heinonen, Ville Kyrki

专题命中工具调用：tool use(abstract)；分类 cs.AI、cs.LG

2306.08810 2023-07-13 cs.LG cs.AI 62%

Deep Generative Models for Decision-Making and Control

Michael Janner

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

Comments UC Berkeley PhD thesis; supersedes arXiv:2010.14496, arXiv:2106.02039, and arXiv:2205.09991

2212.10765 2023-07-04 cs.LG cs.AI 62%

Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search

Taisuke Kobayashi

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments 10 pages, 7 figures

Journal ref Results in Control and Optimization, 2023

2203.15845 2023-06-28 cs.LG cs.AI 62%

Topological Experience Replay

Zhang-Wei Hong, Tao Chen, Yen-Chen Lin, Joni Pajarinen, Pulkit Agrawal

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Journal ref Published at ICLR 2022

2306.10083 2023-06-21 cs.LG cs.AI 62%

Automatic Deduction Path Learning via Reinforcement Learning with Environmental Correction

Shuai Xiao, Chen Pan, Min Wang, Xinxin Zhu, Siqiao Xue, Jing Wang, Yunhua Hu, James Zhang, Jinghua Feng

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

2306.08020 2023-06-16 cs.CL cs.AI 62%

Curatr: A Platform for Semantic Analysis and Curation of Historical Literary Texts

Susan Leavy, Gerardine Meaney, Karen Wade, Derek Greene

专题命中工具调用：workflow(abstract)；分类 cs.AI、cs.CL

Comments 12 pages

Journal ref Metadata and Semantic Research (MTSR 2019), Communications in Computer and Information Science, vol 1057. Springer, Cham

2304.00613 2023-06-13 cs.LG cs.AI 62%

Improving Few-Shot Inductive Learning on Temporal Knowledge Graphs using Confidence-Augmented Reinforcement Learning

Zifeng Ding, Jingpei Wu, Zongyue Li, Yunpu Ma, Volker Tresp

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted to ECML/PKDD 2023

2306.01729 2023-06-05 cs.CL cs.AI 62%

Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans

Stefania Raimondo, Christopher Pal, Xiaotian Liu, David Vazquez, Hector Palacios

专题命中工具调用：workflow(abstract)；分类 cs.AI、cs.CL

2212.09736 2023-05-04 cs.CL cs.AI 62%

Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments

Yu Gu, Xiang Deng, Yu Su

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.CL

Comments 18 pages, 6 figures, 6 tables; accepted to ACL'2023

2304.14698 2023-05-01 cs.LG cs.AI 62%

X-RLflow: Graph Reinforcement Learning for Neural Network Subgraphs Transformation

Guoliang He, Sean Parker, Eiko Yoneki

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments MLSys 2023

2303.13228 2023-03-24 cs.LG cs.AI cs.SY eess.SY stat.ML 62%

Enriching Neural Network Training Dataset to Improve Worst-Case Performance Guarantees

Rahul Nellikkath, Spyros Chatzivasileiadis

专题命中工具调用：tool use(abstract)；分类 cs.AI、cs.LG

Comments arXiv admin note: text overlap with arXiv:2212.10930

2303.10182 2023-03-21 cs.LG cs.AI cs.NE 62%

SFE: A Simple, Fast and Efficient Feature Selection Algorithm for High-Dimensional Data

Behrouz Ahadzadeh, Moloud Abdar, Fatemeh Safara, Abbas Khosravi, Mohammad Bagher Menhaj, Ponnuthurai Nagaratnam Suganthan

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

2302.07940 2023-02-17 cs.RO cs.AI cs.LG 62%

Online Tool Selection with Learned Grasp Prediction Models

Khashayar Rohanimanesh, Jake Metzger, William Richards, Aviv Tamar

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

Comments 14 pages (including the cover page), 5 Figures, Technical Report, OSARO Inc

2207.12805 2023-02-03 q-bio.QM cs.AI cs.LG q-bio.GN 62%

Neural Design for Genetic Perturbation Experiments

Aldo Pacchiano, Drausin Wulsin, Robert A. Barton, Luis Voloch

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

Comments 22 pages main, 15 pages appendix

2205.13134 2023-02-03 cs.AI cs.LG cs.SC nlin.CD physics.comp-ph 62%

Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search

Fangzheng Sun, Yang Liu, Jian-Xun Wang, Hao Sun

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments 22 pages

Journal ref ICLR 2023

2211.10688 2023-01-24 cs.CL cs.AI 62%

ReInform: Selecting paths with reinforcement learning for contextualized link prediction

Marina Speranskaya, Sameh Methias, Benjamin Roth

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.CL

2212.03978 2023-01-12 cs.LG cs.AI 62%

Learning Graph Search Heuristics

Michal Pándy, Weikang Qiu, Gabriele Corso, Petar Veličković, Rex Ying, Jure Leskovec, Pietro Liò

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

2212.11083 2023-01-03 cs.LG cs.AI cs.IT math.IT 62%

Adapting the Exploration Rate for Value-of-Information-Based Reinforcement Learning

Isaac J. Sledge, Jose C. Principe

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Submitted to the IEEE Transactions on Information Theory

2212.14849 2023-01-02 cs.LG cs.AI 62%

Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search

Wenqing Zheng, S P Sharan, Zhiwen Fan, Kevin Wang, Yihan Xi, Zhangyang Wang

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

2205.10124 2022-12-28 cs.AI astro-ph.EP astro-ph.IM cs.LG 62%

The Fellowship of the Dyson Ring: ACT&Friends' Results and Methods for GTOC 11

Marcus Märtens, Dario Izzo, Emmanuel Blazquez, Moritz von Looz, Pablo Gómez, Anne Mergy, Giacomo Acciarini, Chit Hong Yam, Javier Hernando Ayuso, Yuri Shimane

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

2212.11730 2022-12-23 cs.AI cs.LG 62%

TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers

Daniil Kirilenko, Anton Andreychuk, Aleksandr Panov, Konstantin Yakovlev

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

Comments Pre-print of the paper accepted to AAAI'23

2211.12615 2022-11-24 cs.CL cs.AI 62%

AutoReply: Detecting Nonsense in Dialogue Introspectively with Discriminative Replies

Weiyan Shi, Emily Dinan, Adi Renduchintala, Daniel Fried, Athul Paul Jacob, Zhou Yu, Mike Lewis

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.CL

2211.06721 2022-11-15 cs.LG cs.AI 62%

Using Features at Multiple Temporal and Spatial Resolutions to Predict Human Behavior in Real Time

Liang Zhang, Justin Lieffers, Adarsh Pyarelal

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Presented at AAAI Fall 2021 Symposium on ToM for Teams, to be published as a chapter in a Springer volume

2211.03769 2022-11-08 cs.AI cs.LG cs.RO 62%

Are AlphaZero-like Agents Robust to Adversarial Perturbations?

Li-Cheng Lan, Huan Zhang, Ti-Rong Wu, Meng-Yu Tsai, I-Chen Wu, Cho-Jui Hsieh

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted by Neurips 2022

2206.08569 2022-10-19 cs.LG cs.AI cs.RO 62%

Bootstrapped Transformer for Offline Reinforcement Learning

Kerong Wang, Hanye Zhao, Xufang Luo, Kan Ren, Weinan Zhang, Dongsheng Li

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted in NeurIPS 2022

2103.06846 2022-10-12 cs.LG cs.AI cs.NE 62%

Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with

Paul Ecoffet, Nicolas Fontbonne, Jean-Baptiste André, Nicolas Bredeche

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

2210.05125 2022-10-12 cs.AI cs.LG cs.MA 62%

Human-AI Coordination via Human-Regularized Search and Learning

Hengyuan Hu, David J Wu, Adam Lerer, Jakob Foerster, Noam Brown

专题命中工具调用：AI agent(abstract)；分类 cs.AI、cs.LG

2109.08548 2022-10-12 cs.DC cs.AI cs.LG cs.PF cs.SY eess.SY 62%

Load Balancing in Compute Clusters with Delayed Feedback

Anam Tahir, Bastian Alt, Amr Rizk, Heinz Koeppl

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted at IEEE Transactions on Computers 2022

2111.06266 2022-09-21 cs.LG cs.AI 62%

AlphaDDA: Strategies for Adjusting the Playing Strength of a Fully Trained AlphaZero System to a Suitable Human Training Partner

Kazuhisa Fujita

专题命中工具调用：AI agent(abstract)；分类 cs.AI、cs.LG

Comments 24 pages, 10 figures

1. 工具调用 5118 篇

Cyclophobic Reinforcement Learning

Learning representations that are closed-form Monge mapping optimal with application to domain adaptation

Deep Generative Models for Decision-Making and Control

Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search

Topological Experience Replay

Automatic Deduction Path Learning via Reinforcement Learning with Environmental Correction

Curatr: A Platform for Semantic Analysis and Curation of Historical Literary Texts

Improving Few-Shot Inductive Learning on Temporal Knowledge Graphs using Confidence-Augmented Reinforcement Learning

Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans

Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments

X-RLflow: Graph Reinforcement Learning for Neural Network Subgraphs Transformation

Enriching Neural Network Training Dataset to Improve Worst-Case Performance Guarantees

SFE: A Simple, Fast and Efficient Feature Selection Algorithm for High-Dimensional Data

Online Tool Selection with Learned Grasp Prediction Models

Neural Design for Genetic Perturbation Experiments

Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search

ReInform: Selecting paths with reinforcement learning for contextualized link prediction

Learning Graph Search Heuristics

Adapting the Exploration Rate for Value-of-Information-Based Reinforcement Learning

Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search

The Fellowship of the Dyson Ring: ACT&Friends' Results and Methods for GTOC 11

TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers

AutoReply: Detecting Nonsense in Dialogue Introspectively with Discriminative Replies

Using Features at Multiple Temporal and Spatial Resolutions to Predict Human Behavior in Real Time

Are AlphaZero-like Agents Robust to Adversarial Perturbations?

Bootstrapped Transformer for Offline Reinforcement Learning

Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with

Human-AI Coordination via Human-Regularized Search and Learning

Load Balancing in Compute Clusters with Delayed Feedback

AlphaDDA: Strategies for Adjusting the Playing Strength of a Fully Trained AlphaZero System to a Suitable Human Training Partner