AI Agent - arXivDaily 专题

2312.10289 2023-12-19 cs.LG cs.AI cs.SY eess.SY 62%

Active Reinforcement Learning for Robust Building Control

Doseok Jang, Larry Yan, Lucas Spangher, Costas Spanos

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

2311.02227 2023-12-13 cs.LG cs.AI cs.SY eess.SY 62%

State-Wise Safe Reinforcement Learning With Pixel Observations

Simon Sinong Zhan, Yixuan Wang, Qingyuan Wu, Ruochen Jiao, Chao Huang, Qi Zhu

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

Comments 10 pages, 5 figures

2305.04082 2023-12-01 cs.LG cs.CL 62%

A Minimal Approach for Natural Language Action Space in Text-based Games

Dongwon Kelvin Ryu, Meng Fang, Shirui Pan, Gholamreza Haffari, Ehsan Shareghi

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

2311.14674 2023-11-28 cs.CL cs.AI cs.IT math.IT 62%

Emotion-Oriented Behavior Model Using Deep Learning

Muhammad Arslan Raza, Muhammad Shoaib Farooq, Adel Khelifi, Atif Alvi

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

2311.11462 2023-11-27 cs.CL cs.AI 62%

LLM aided semi-supervision for Extractive Dialog Summarization

Nishant Mishra, Gaurav Sahu, Iacer Calixto, Ameen Abu-Hanna, Issam H. Laradji

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

Comments to be published in EMNLP Findings

2311.11557 2023-11-21 cs.LG cs.AI 62%

Replay-enhanced Continual Reinforcement Learning

Tiantian Zhang, Kevin Zehua Shen, Zichuan Lin, Bo Yuan, Xueqian Wang, Xiu Li, Deheng Ye

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

Comments Accepted by Transactions on Machine Learning Research 2023

2311.10607 2023-11-20 eess.SY cs.AI cs.DC cs.LG cs.SY 62%

Active Inference on the Edge: A Design Study

Boris Sedlak, Victor Casamayor Pujol, Praveen Kumar Donta, Schahram Dustdar

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

2310.20654 2023-11-20 cs.LG cs.AI 62%

Closed Drafting as a Case Study for First-Principle Interpretability, Memory, and Generalizability in Deep Reinforcement Learning

Ryan Rezai, Jason Wang

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

Comments 4 pages, 4 figures, equal contribution

2311.07708 2023-11-15 cs.AI cs.CE cs.LG 62%

Reinforcement Learning for Solving Stochastic Vehicle Routing Problem

Zangir Iklassov, Ikboljon Sobirov, Ruben Solozabal, Martin Takac

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

Comments 14 pages, accepted to ACML24

2311.07578 2023-11-15 cs.CV cs.AI cs.LG 62%

A Metacognitive Approach to Out-of-Distribution Detection for Segmentation

Meghna Gummadi, Cassandra Kent, Karl Schmeckpeper, Eric Eaton

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

2311.03651 2023-11-08 cs.LG cs.AI cs.RO 62%

SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations

Chan Kim, Jaekyung Cho, Christophe Bobda, Seung-Woo Seo, Seong-Woo Kim

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

Comments 9 pages, 5 figures. Proceedings of the 32nd International Joint Conference on Artificial Intelligence, 2023

2311.02171 2023-11-08 cs.LG cs.AI 62%

Emergence of Abstract State Representations in Embodied Sequence Modeling

Tian Yun, Zilai Zeng, Kunal Handa, Ashish V. Thapliyal, Bo Pang, Ellie Pavlick, Chen Sun

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

Comments Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023). Project webpage: https://abstract-state-seqmodel.github.io/

2311.00426 2023-11-02 cs.LG cs.AI 62%

Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards

Alain Andres, Daochen Zha, Javier Del Ser

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

Comments 7 pages, 5 figures

2306.15156 2023-10-31 cs.LG cs.AI 62%

Learning non-Markovian Decision-Making from State-only Sequences

Aoyang Qin, Feng Gao, Qing Li, Song-Chun Zhu, Sirui Xie

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

Comments Accepted at NeurIPS 2023

2310.17537 2023-10-27 cs.AI cs.LG 62%

Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity

Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete

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

Comments NeurIPS 2023 Workshop - Intrinsically Motivated Open-ended Learning

2303.03284 2023-10-27 cs.LG cs.AI 62%

The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models

Raphael Avalos, Florent Delgrange, Ann Nowé, Guillermo A. Pérez, Diederik M. Roijers

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

2310.16686 2023-10-26 cs.AI cs.LG 62%

Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies

Michael Beukman, Devon Jarvis, Richard Klein, Steven James, Benjamin Rosman

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

Comments Accepted to NeurIPS 2023

2310.08702 2023-10-16 cs.LG cs.AI cs.RO 62%

ELDEN: Exploration via Local Dependencies

Jiaheng Hu, Zizhao Wang, Peter Stone, Roberto Martin-Martin

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

Comments Accepted to NeurIPS 2023

2310.08549 2023-10-13 cs.LG cs.AI cs.RO 62%

Cross-Episodic Curriculum for Transformer Agents

Lucy Xiaoyang Shi, Yunfan Jiang, Jake Grigsby, Linxi "Jim" Fan, Yuke Zhu

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

Comments To appear in NeurIPS 2023; The first two authors contributed equally

2310.02717 2023-10-11 cs.LG cs.AI 62%

Online Clustering of Bandits with Misspecified User Models

Zhiyong Wang, Jize Xie, Xutong Liu, Shuai Li, John C. S. Lui

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

2309.08827 2023-09-19 cs.CL cs.AI 62%

S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs

Sarkar Snigdha Sarathi Das, Chirag Shah, Mengting Wan, Jennifer Neville, Longqi Yang, Reid Andersen, Georg Buscher, Tara Safavi

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

2309.06126 2023-09-13 astro-ph.IM astro-ph.CO astro-ph.GA astro-ph.HE cs.CL cs.LG 62%

AstroLLaMA: Towards Specialized Foundation Models in Astronomy

Tuan Dung Nguyen, Yuan-Sen Ting, Ioana Ciucă, Charlie O'Neill, Ze-Chang Sun, Maja Jabłońska, Sandor Kruk, Ernest Perkowski, Jack Miller, Jason Li, Josh Peek, Kartheik Iyer, Tomasz Różański, Pranav Khetarpal, Sharaf Zaman, David Brodrick, Sergio J. Rodríguez Méndez, Thang Bui, Alyssa Goodman, Alberto Accomazzi, Jill Naiman, Jesse Cranney, Kevin Schawinski, UniverseTBD

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

Comments 6 pages, 3 figures, submitted to IJCNLP-AACL 2023. Comments are welcome. The model can be found on Hugging Face - https://huggingface.co/universeTBD/astrollama

2212.14214 2023-09-06 cs.AI cs.LG 62%

Backward Curriculum Reinforcement Learning

KyungMin Ko

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

Comments In the proceedings of the 32nd IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2023)

2010.08657 2023-08-08 cs.LG cs.AI cs.CV 62%

Class-incremental Learning with Pre-allocated Fixed Classifiers

Federico Pernici, Matteo Bruni, Claudio Baecchi, Francesco Turchini, Alberto Del Bimbo

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

Comments ICPR 2021 (figure and typos fixed)

2308.01872 2023-08-04 cs.AI cs.CL 62%

Thespian: Multi-Character Text Role-Playing Game Agents

Christopher Cui, Xiangyu Peng, Mark Riedl

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

Comments 11 pages

2111.03110 2023-08-04 cs.LG cs.AI 62%

Successor Feature Neural Episodic Control

David Emukpere, Xavier Alameda-Pineda, Chris Reinke

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

2307.11044 2023-07-21 cs.LG cs.AI 62%

On the Convergence of Bounded Agents

David Abel, André Barreto, Hado van Hasselt, Benjamin Van Roy, Doina Precup, Satinder Singh

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

2211.15944 2023-07-14 cs.LG cs.AI 62%

The Effectiveness of World Models for Continual Reinforcement Learning

Samuel Kessler, Mateusz Ostaszewski, Michał Bortkiewicz, Mateusz Żarski, Maciej Wołczyk, Jack Parker-Holder, Stephen J. Roberts, Piotr Miłoś

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

Comments Accepted at CoLLAs 2023, 21 pages, 15 figures

2307.02502 2023-07-07 q-bio.OT cs.AI cs.CL 62%

Math Agents: Computational Infrastructure, Mathematical Embedding, and Genomics

Melanie Swan, Takashi Kido, Eric Roland, Renato P. dos Santos

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

2306.12806 2023-06-23 q-fin.TR cs.AI cs.CE cs.LG 62%

Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness

Andrea Coletta, Joseph Jerome, Rahul Savani, Svitlana Vyetrenko

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

1. 记忆与上下文管理 4753 篇

Active Reinforcement Learning for Robust Building Control

State-Wise Safe Reinforcement Learning With Pixel Observations

A Minimal Approach for Natural Language Action Space in Text-based Games

Emotion-Oriented Behavior Model Using Deep Learning

LLM aided semi-supervision for Extractive Dialog Summarization

Replay-enhanced Continual Reinforcement Learning

Active Inference on the Edge: A Design Study

Closed Drafting as a Case Study for First-Principle Interpretability, Memory, and Generalizability in Deep Reinforcement Learning

Reinforcement Learning for Solving Stochastic Vehicle Routing Problem

A Metacognitive Approach to Out-of-Distribution Detection for Segmentation

SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations

Emergence of Abstract State Representations in Embodied Sequence Modeling

Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards

Learning non-Markovian Decision-Making from State-only Sequences

Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity

The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models

Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies

ELDEN: Exploration via Local Dependencies

Cross-Episodic Curriculum for Transformer Agents

Online Clustering of Bandits with Misspecified User Models

S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs

AstroLLaMA: Towards Specialized Foundation Models in Astronomy

Backward Curriculum Reinforcement Learning

Class-incremental Learning with Pre-allocated Fixed Classifiers

Thespian: Multi-Character Text Role-Playing Game Agents

Successor Feature Neural Episodic Control

On the Convergence of Bounded Agents

The Effectiveness of World Models for Continual Reinforcement Learning

Math Agents: Computational Infrastructure, Mathematical Embedding, and Genomics

Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness