AI Agent - arXivDaily 专题

2305.10697 2023-12-14 cs.LG stat.ML 57%

The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond

Jiin Woo, Gauri Joshi, Yuejie Chi

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Short version at ICML 2023

2312.04216 2023-12-08 cs.LG 57%

CODEX: A Cluster-Based Method for Explainable Reinforcement Learning

Timothy K. Mathes, Jessica Inman, Andrés Colón, Simon Khan

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Presented at the International Joint Conference on Artificial Intelligence (IJCAI) 2023 Workshop on Explainable Artificial Intelligence (XAI)

2106.00198 2023-12-08 cs.LG cs.GT cs.MA math.OC 57%

Gradient play in stochastic games: stationary points, convergence, and sample complexity

Runyu Zhang, Zhaolin Ren, Na Li

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2310.15890 2023-12-07 cs.LG 57%

Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data

Sai Aparna Aketi, Kaushik Roy

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 12 pages, 7 figures, 11 tables. arXiv admin note: text overlap with arXiv:2305.04792

Journal ref IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024

2310.03915 2023-12-01 cs.LG 57%

Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control

Neehal Tumma, Mathias Lechner, Noel Loo, Ramin Hasani, Daniela Rus

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

2311.15089 2023-11-28 cs.LG 57%

Where2Start: Leveraging initial States for Robust and Sample-Efficient Reinforcement Learning

Pouya Parsa, Raoof Zare Moayedi, Mohammad Bornosi, Mohammad Mahdi Bejani

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 9 pages, 3 figures

2303.03982 2023-11-27 cs.LG 57%

Structured State Space Models for In-Context Reinforcement Learning

Chris Lu, Yannick Schroecker, Albert Gu, Emilio Parisotto, Jakob Foerster, Satinder Singh, Feryal Behbahani

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2311.08719 2023-11-16 cs.CL 57%

Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory

Lei Liu, Xiaoyan Yang, Yue Shen, Binbin Hu, Zhiqiang Zhang, Jinjie Gu, Guannan Zhang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

2307.09831 2023-11-14 cs.AI 57%

A Fast and Map-Free Model for Trajectory Prediction in Traffics

Junhong Xiang, Jingmin Zhang, Zhixiong Nan

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 7 pages, 3 figures

2308.03811 2023-11-10 math.OC cs.LG 57%

Non-Convex Bilevel Optimization with Time-Varying Objective Functions

Sen Lin, Daouda Sow, Kaiyi Ji, Yingbin Liang, Ness Shroff

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Journal ref NeurIPS 2023

2311.03893 2023-11-08 cs.AI q-bio.NC 57%

Understanding Tool Discovery and Tool Innovation Using Active Inference

Poppy Collis, Paul F Kinghorn, Christopher L Buckley

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 13 pages, 8 pages, accepted for International Workshop on Active Inference 2023, due to be published in IWAI 2023, CCIS 1915 proceedings (Springer) 2024

2311.03021 2023-11-07 cs.CL 57%

Detecting agreement in multi-party dialogue: evaluating speaker diarisation versus a procedural baseline to enhance user engagement

Angus Addlesee, Daniel Denley, Andy Edmondson, Nancie Gunson, Daniel Hernández Garcia, Alexandre Kha, Oliver Lemon, James Ndubuisi, Neil O'Reilly, Lia Perochaud, Raphaël Valeri, Miebaka Worika

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments Proceedings of the workshop on advancing GROup UNderstanding and robots aDaptive behaviour (GROUND), 2023

2011.07989 2023-11-07 cs.LG stat.ML 57%

A New Bandit Setting Balancing Information from State Evolution and Corrupted Context

Alexander Galozy, Slawomir Nowaczyk, Mattias Ohlsson

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2310.20479 2023-11-01 cs.CL 57%

Multi-User MultiWOZ: Task-Oriented Dialogues among Multiple Users

Yohan Jo, Xinyan Zhao, Arijit Biswas, Nikoletta Basiou, Vincent Auvray, Nikolaos Malandrakis, Angeliki Metallinou, Alexandros Potamianos

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments To Appear in EMNLP-Findings 2023

2310.18803 2023-10-31 cs.LG 57%

Weakly Coupled Deep Q-Networks

Ibrahim El Shar, Daniel R. Jiang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments To appear in proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023)

2309.01522 2023-10-27 cs.CL 57%

What are Public Concerns about ChatGPT? A Novel Self-Supervised Neural Topic Model Tells You

Rui Wang, Xing Liu, Yanan Wang, Haiping Huang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments The paper requires major revision

2310.16135 2023-10-26 cs.CL 57%

Can You Follow Me? Testing Situational Understanding in ChatGPT

Chenghao Yang, Allyson Ettinger

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

Comments EMNLP 2023 Main Paper (Camera Ready)

2308.04600 2023-10-25 cs.AI cs.LO cs.SC 57%

Model of models -- Part 1

Shimon Komarovsky

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments arXiv admin note: text overlap with arXiv:2301.13556

2305.13829 2023-10-25 cs.CL 57%

Learning from Mistakes via Cooperative Study Assistant for Large Language Models

Danqing Wang, Lei Li

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments Accepted by EMNLP 2023 main conference

2310.15066 2023-10-24 cs.CV cs.CL 57%

Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge

Te-Lin Wu, Yu Zhou, Nanyun Peng

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

Comments In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2310.09924 2023-10-17 cs.LG 57%

Deep Reinforcement Learning with Explicit Context Representation

Francisco Munguia-Galeano, Ah-Hwee Tan, Ze Ji

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Manuscript accepted for publication as regular paper in IEEE Transactions on Neural Networks and Learning Systems

2310.06777 2023-10-11 cs.LG 57%

Information Content Exploration

Jacob Chmura, Hasham Burhani, Xiao Qi Shi

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 12 pages, 12 figures

2310.05029 2023-10-10 cs.CL 57%

Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading

Howard Chen, Ramakanth Pasunuru, Jason Weston, Asli Celikyilmaz

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

2307.11546 2023-10-06 physics.plasm-ph cs.LG 57%

Towards practical reinforcement learning for tokamak magnetic control

Brendan D. Tracey, Andrea Michi, Yuri Chervonyi, Ian Davies, Cosmin Paduraru, Nevena Lazic, Federico Felici, Timo Ewalds, Craig Donner, Cristian Galperti, Jonas Buchli, Michael Neunert, Andrea Huber, Jonathan Evens, Paula Kurylowicz, Daniel J. Mankowitz, Martin Riedmiller, The TCV Team

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2105.07099 2023-10-06 cs.LG 57%

Feature-Based Interpretable Reinforcement Learning based on State-Transition Models

Omid Davoodi, Majid Komeili

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2310.01439 2023-10-04 cs.MA cs.AI 57%

Making Friends in the Dark: Ad Hoc Teamwork Under Partial Observability

João G. Ribeiroa, Cassandro Martinhoa, Alberto Sardinhaa, Francisco S. Melo

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments arXiv admin note: text overlap with arXiv:2201.03538

2304.04916 2023-10-04 cs.LG stat.ML 57%

A Data-Driven State Aggregation Approach for Dynamic Discrete Choice Models

Sinong Geng, Houssam Nassif, Carlos A. Manzanares

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Journal ref The Conference on Uncertainty in Artificial Intelligence (UAI'23), Pittsburgh, PA, pp. 647-657, 2023

2309.09125 2023-09-19 cs.AI 57%

Using Reinforcement Learning to Simplify Mealtime Insulin Dosing for People with Type 1 Diabetes: In-Silico Experiments

Anas El Fathi, Marc D. Breton

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 6 pages, 4 figures, conference

2309.06896 2023-09-14 cs.LG 57%

Domain-Aware Augmentations for Unsupervised Online General Continual Learning

Nicolas Michel, Romain Negrel, Giovanni Chierchia, Jean-François Bercher

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted to BMVC'23

2309.05346 2023-09-12 cs.LG cs.CV 57%

Learning Geometric Representations of Objects via Interaction

Alfredo Reichlin, Giovanni Luca Marchetti, Hang Yin, Anastasiia Varava, Danica Kragic

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1. 记忆与上下文管理 4758 篇

The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond

CODEX: A Cluster-Based Method for Explainable Reinforcement Learning

Gradient play in stochastic games: stationary points, convergence, and sample complexity

Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data

Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control

Where2Start: Leveraging initial States for Robust and Sample-Efficient Reinforcement Learning

Structured State Space Models for In-Context Reinforcement Learning

Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory

A Fast and Map-Free Model for Trajectory Prediction in Traffics

Non-Convex Bilevel Optimization with Time-Varying Objective Functions

Understanding Tool Discovery and Tool Innovation Using Active Inference

Detecting agreement in multi-party dialogue: evaluating speaker diarisation versus a procedural baseline to enhance user engagement

A New Bandit Setting Balancing Information from State Evolution and Corrupted Context

Multi-User MultiWOZ: Task-Oriented Dialogues among Multiple Users

Weakly Coupled Deep Q-Networks

What are Public Concerns about ChatGPT? A Novel Self-Supervised Neural Topic Model Tells You

Can You Follow Me? Testing Situational Understanding in ChatGPT

Model of models -- Part 1

Learning from Mistakes via Cooperative Study Assistant for Large Language Models

Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge

Deep Reinforcement Learning with Explicit Context Representation

Information Content Exploration

Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading

Towards practical reinforcement learning for tokamak magnetic control

Feature-Based Interpretable Reinforcement Learning based on State-Transition Models

Making Friends in the Dark: Ad Hoc Teamwork Under Partial Observability

A Data-Driven State Aggregation Approach for Dynamic Discrete Choice Models

Using Reinforcement Learning to Simplify Mealtime Insulin Dosing for People with Type 1 Diabetes: In-Silico Experiments

Domain-Aware Augmentations for Unsupervised Online General Continual Learning

Learning Geometric Representations of Objects via Interaction