Výsledky vyhledávání - "ML: Reinforcement Learning Algorithms"

On the Sample Complexity of Representation Learning in Multi-Task Bandits with Global and Local Structure

Autoři: Russo, Alessio Proutiere, Alexandre

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence. :9658-9667

Témata: ML: Representation Learning, ML: Online Learning & Bandits, ML: Reinforcement Learning Algorithms, ML: Reinforcement Learning Theory, Mathematical Statistics, Matematisk statistik, Electrical Engineering, Elektro- och systemteknik, Datalogi, Computer Science

Popis souboru: print

Přístupová URL adresa: https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-333761
https://doi.org/10.1609/aaai.v37i8.26155

AdapSafe: Adaptive and Safe-Certified Deep Reinforcement Learning-Based Frequency Control for Carbon-Neutral Power Systems

Autoři: Wan, Xu Sun, Mingyang Chen, Boli a další

Přispěvatelé: Wan, Xu Sun, Mingyang Chen, Boli a další

Zdroj: In: Williams, Brian and Chen, Yiling and Neville, Jennifer, (eds.) Proceedings of the AAAI Conference on Artificial Intelligence. (pp. pp. 5294-5302). AAAI: Washington, D.C., USA. (2023)

Témata: APP: Energy, Environment & Sustainability, ML: Applications, ML: Reinforcement Learning Algorithms, PEAI: Safety, Robustness & Trustworthiness

Popis souboru: text

Relation: https://discovery.ucl.ac.uk/id/eprint/10160010/1/AAAI_Press_Anonymous_SubmissionInstructions_for_Authors_Using_LaTeX.pdf; https://discovery.ucl.ac.uk/id/eprint/10160010/

Dostupnost: https://discovery.ucl.ac.uk/id/eprint/10160010/1/AAAI_Press_Anonymous_SubmissionInstructions_for_Authors_Using_LaTeX.pdf
https://discovery.ucl.ac.uk/id/eprint/10160010/

Selector-Enhancer: Learning Dynamic Selection of Local and Non-local Attention Operation for Speech Enhancement

Autoři: Xu, Xinmeng Tu, Weiping Yang, Yuhong

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 11: AAAI-23 Technical Tracks 11; 13853-13860 ; 2374-3468 ; 2159-5399

Témata: SNLP: Speech and Multimodality, ML: Reinforcement Learning Algorithms

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26622/26394; https://ojs.aaai.org/index.php/AAAI/article/view/26622

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26622
https://doi.org/10.1609/aaai.v37i11.26622

Taming Continuous Posteriors for Latent Variational Dialogue Policies

Autoři: Vlastelica, Marin Ernst, Patrick Szarvas, Gyuri

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 11: AAAI-23 Technical Tracks 11; 13673-13681 ; 2374-3468 ; 2159-5399

Témata: SNLP: Conversational AI/Dialogue Systems, ML: Reinforcement Learning Algorithms, ML: Deep Generative Models & Autoencoders

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26602/26374; https://ojs.aaai.org/index.php/AAAI/article/view/26602

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26602
https://doi.org/10.1609/aaai.v37i11.26602

Cogito Ergo Summ: Abstractive Summarization of Biomedical Papers via Semantic Parsing Graphs and Consistency Rewards

Autoři: Frisoni, Giacomo Italiani, Paolo Salvatori, Stefano a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 11: AAAI-23 Technical Tracks 11; 12781-12789 ; 2374-3468 ; 2159-5399

Témata: SNLP: Summarization, APP: Bioinformatics, ML: Deep Neural Architectures, ML: Reinforcement Learning Algorithms, SNLP: Generation, SNLP: Language Grounding, SNLP: Language Models, SNLP: Learning & Optimization for SNLP, SNLP: Lexical & Frame Semantics, Semantic Parsing, SNLP: Sentence-Level Semantics and Textual Inference, KRR: Other Foundations of Knowledge Representation & Reasoning

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26503/26275; https://ojs.aaai.org/index.php/AAAI/article/view/26503

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26503
https://doi.org/10.1609/aaai.v37i11.26503

End-to-End Deep Reinforcement Learning for Conversation Disentanglement

Autoři: Bhukar, Karan Kumar, Harshit Raghu, Dinesh a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 11: AAAI-23 Technical Tracks 11; 12571-12579 ; 2374-3468 ; 2159-5399

Témata: SNLP: Conversational AI/Dialogue Systems, ML: Reinforcement Learning Algorithms

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26480/26252; https://ojs.aaai.org/index.php/AAAI/article/view/26480

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26480
https://doi.org/10.1609/aaai.v37i11.26480

Large-State Reinforcement Learning for Hyper-Heuristics

Autoři: Kletzander, Lucas Musliu, Nysret

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 12444-12452 ; 2374-3468 ; 2159-5399

Témata: SO: Metareasoning and Metaheuristics, ML: Reinforcement Learning Algorithms, PRS: Applications, SO: Heuristic Search

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26466/26238; https://ojs.aaai.org/index.php/AAAI/article/view/26466

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26466
https://doi.org/10.1609/aaai.v37i10.26466

Neural TSP Solver with Progressive Distillation

Autoři: Zhang, Dongxiang Xiao, Ziyang Wang, Yuan a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 12147-12154 ; 2374-3468 ; 2159-5399

Témata: PRS: Planning/Scheduling and Learning, ML: Reinforcement Learning Algorithms

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26432/26204; https://ojs.aaai.org/index.php/AAAI/article/view/26432

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26432
https://doi.org/10.1609/aaai.v37i10.26432

A Dynamics and Task Decoupled Reinforcement Learning Architecture for High-Efficiency Dynamic Target Intercept

Autoři: Liu, Dora D. Hu, Liang Zhang, Qi a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 12049-12057 ; 2374-3468 ; 2159-5399

Témata: PRS: Applications, ROB: Motion and Path Planning, ML: Reinforcement Learning Algorithms, PRS: Optimization of Spatio-Temporal Systems, PRS: Other Foundations of Planning, Routing & Scheduling, PRS: Planning Under Uncertainty

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26421/26193; https://ojs.aaai.org/index.php/AAAI/article/view/26421

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26421
https://doi.org/10.1609/aaai.v37i10.26421

Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information Principles

Autoři: Zeng, Xianghua Peng, Hao Li, Angsheng

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 11772-11780 ; 2374-3468 ; 2159-5399

Témata: MAS: Multiagent Learning, ML: Reinforcement Learning Algorithms

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26390/26162; https://ojs.aaai.org/index.php/AAAI/article/view/26390

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26390
https://doi.org/10.1609/aaai.v37i10.26390

DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learning

Autoři: Yuan, Tingting Chung, Hwei-Ming Yuan, Jie a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 11763-11771 ; 2374-3468 ; 2159-5399

Témata: MAS: Agent Communication, ML: Reinforcement Learning Algorithms, ML: Reinforcement Learning Theory, MAS: Multiagent Learning

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26389/26161; https://ojs.aaai.org/index.php/AAAI/article/view/26389

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26389
https://doi.org/10.1609/aaai.v37i10.26389

Hierarchical Mean-Field Deep Reinforcement Learning for Large-Scale Multiagent Systems

Autoři: Yu, Chao

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 11744-11752 ; 2374-3468 ; 2159-5399

Témata: MAS: Multiagent Learning, ML: Reinforcement Learning Algorithms

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26387/26159; https://ojs.aaai.org/index.php/AAAI/article/view/26387

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26387
https://doi.org/10.1609/aaai.v37i10.26387

Subspace-Aware Exploration for Sparse-Reward Multi-Agent Tasks

Autoři: Xu, Pei Zhang, Junge Yin, Qiyue a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 11717-11725 ; 2374-3468 ; 2159-5399

Témata: MAS: Multiagent Learning, ML: Reinforcement Learning Algorithms

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26384/26156; https://ojs.aaai.org/index.php/AAAI/article/view/26384

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26384
https://doi.org/10.1609/aaai.v37i10.26384

DM²: Decentralized Multi-Agent Reinforcement Learning via Distribution Matching

Autoři: Wang, Caroline Durugkar, Ishan Liebman, Elad a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 11699-11707 ; 2374-3468 ; 2159-5399

Témata: MAS: Coordination and Collaboration, MAS: Multiagent Learning, MAS: Distributed Problem Solving, ML: Reinforcement Learning Algorithms, ML: Imitation Learning & Inverse Reinforcement Learning

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26382/26154; https://ojs.aaai.org/index.php/AAAI/article/view/26382

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26382
https://doi.org/10.1609/aaai.v37i10.26382

Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition

Autoři: Liu, Shunyu Zhou, Yihe Song, Jie a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 11595-11603 ; 2374-3468 ; 2159-5399

Témata: MAS: Multiagent Learning, ML: Reinforcement Learning Algorithms, MAS: Agent-Based Simulation and Emergent Behavior, MAS: Coordination and Collaboration

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26370/26142; https://ojs.aaai.org/index.php/AAAI/article/view/26370

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26370
https://doi.org/10.1609/aaai.v37i10.26370

Reward-Based Negotiating Agent Strategies

Autoři: Higa, Ryota Fujita, Katsuhide Takahashi, Toki a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 11569-11577 ; 2374-3468 ; 2159-5399

Témata: MAS: Agreement, Argumentation & Negotiation, GTEP: Negotiation and Contract-Based Systems, ML: Applications, ML: Reinforcement Learning Algorithms, MAS: Agent/AI Theories and Architectures, MAS: Coordination and Collaboration

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26367/26139; https://ojs.aaai.org/index.php/AAAI/article/view/26367

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26367
https://doi.org/10.1609/aaai.v37i10.26367

Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient

Autoři: Chen, Wubing Li, Wenbin Liu, Xiao a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 10: AAAI-23 Technical Tracks 10; 11542-11550 ; 2374-3468 ; 2159-5399

Témata: MAS: Multiagent Learning, MAS: Coordination and Collaboration, ML: Reinforcement Learning Algorithms, GTEP: Cooperative Game Theory

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26364/26136; https://ojs.aaai.org/index.php/AAAI/article/view/26364

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26364
https://doi.org/10.1609/aaai.v37i10.26364

Gradient-Adaptive Pareto Optimization for Constrained Reinforcement Learning

Autoři: Zhou, Zixian Huang, Mengda Pan, Feiyang a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 9: AAAI-23 Technical Tracks 9; 11443-11451 ; 2374-3468 ; 2159-5399

Témata: ML: Reinforcement Learning Algorithms, ML: Applications, ML: Deep Learning Theory, ML: Optimization, ML: Reinforcement Learning Theory

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26353/26125; https://ojs.aaai.org/index.php/AAAI/article/view/26353

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26353
https://doi.org/10.1609/aaai.v37i9.26353

Adaptive Policy Learning for Offline-to-Online Reinforcement Learning

Autoři: Zheng, Han Luo, Xufang Wei, Pengfei a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 9: AAAI-23 Technical Tracks 9; 11372-11380 ; 2374-3468 ; 2159-5399

Témata: ML: Reinforcement Learning Algorithms

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26345/26117; https://ojs.aaai.org/index.php/AAAI/article/view/26345

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26345
https://doi.org/10.1609/aaai.v37i9.26345

DARL: Distance-Aware Uncertainty Estimation for Offline Reinforcement Learning

Autoři: Zhang, Hongchang Shao, Jianzhun He, Shuncheng a další

Zdroj: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 37 No. 9: AAAI-23 Technical Tracks 9; 11210-11218 ; 2374-3468 ; 2159-5399

Témata: ML: Reinforcement Learning Algorithms

Popis souboru: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/26327/26099; https://ojs.aaai.org/index.php/AAAI/article/view/26327

Dostupnost: https://ojs.aaai.org/index.php/AAAI/article/view/26327
https://doi.org/10.1609/aaai.v37i9.26327