AI Agent - arXivDaily 专题

2210.09255 2022-10-18 cs.LG stat.ML 57%

A Unified Algorithm for Stochastic Path Problems

Christoph Dann, Chen-Yu Wei, Julian Zimmert

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2210.04137 2022-10-14 cs.LG cs.CV cs.RO 57%

Few-Shot Continual Active Learning by a Robot

Ali Ayub, Carter Fendley

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted at NeurIPS 2022

2102.09703 2022-10-14 cs.LG 57%

Near-Optimal Randomized Exploration for Tabular Markov Decision Processes

Zhihan Xiong, Ruoqi Shen, Qiwen Cui, Maryam Fazel, Simon S. Du

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

Comments 41 pages, 3 figures, Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)

2011.04590 2022-10-12 cs.AI 57%

From Eye-blinks to State Construction: Diagnostic Benchmarks for Online Representation Learning

Banafsheh Rafiee, Zaheer Abbas, Sina Ghiassian, Raksha Kumaraswamy, Richard Sutton, Elliot Ludvig, Adam White

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2205.12662 2022-10-11 cs.CL 57%

DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning

Zhi Chen, Jijia Bao, Lu Chen, Yuncong Liu, Da Ma, Bei Chen, Mengyue Wu, Su Zhu, Xin Dong, Fujiang Ge, Qingliang Miao, Jian-Guang Lou, Kai Yu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments Work in Progress

2210.03528 2022-10-10 cs.LG cs.IT math.IT stat.ML 57%

Tractable Optimality in Episodic Latent MABs

Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments NeurIPS 2022

1910.07421 2022-10-10 cs.NI cs.LG 57%

Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use case

Paul Almasan, José Suárez-Varela, Krzysztof Rusek, Pere Barlet-Ros, Albert Cabellos-Aparicio

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 12 pages

2209.15256 2022-10-03 cs.LG cs.CV cs.RO 57%

S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

Daesol Cho, Dongseok Shim, H. Jin Kim

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments NeurIPS 2022, first two authors contributed equally

2209.14414 2022-09-30 stat.ML cs.LG 57%

Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees

Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Remi Munos, Alexey Naumov, Mark Rowland, Michal Valko, Pierre Menard

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments arXiv admin note: text overlap with arXiv:2205.07704

2209.12687 2022-09-27 cs.CL cs.CY 57%

A Case Report On The "A.I. Locked-In Problem": social concerns with modern NLP

Yoshija Walter

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments 17 pages

2209.07215 2022-09-16 cs.CR cs.LG 57%

ProAPT: Projection of APT Threats with Deep Reinforcement Learning

Motahareh Dehghan, Babak Sadeghiyan, Erfan Khosravian, Alireza Sedighi Moghaddam, Farshid Nooshi

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2209.05333 2022-09-13 cs.LG cs.RO 57%

Self-supervised Sequential Information Bottleneck for Robust Exploration in Deep Reinforcement Learning

Bang You, Jingming Xie, Youping Chen, Jan Peters, Oleg Arenz

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 14 pages

2102.07937 2022-09-12 cs.LG stat.ML 57%

Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees

Gregory Dexter, Kevin Bello, Jean Honorio

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Journal ref Neural Information Processing Systems (NeurIPS), 2021

2209.02562 2022-09-07 cs.AI 57%

Project proposal: A modular reinforcement learning based automated theorem prover

Boris Shminke

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 6 pages, submitted to AITP (http://aitp-conference.org/2022/)

2209.00988 2022-09-05 eess.SP cs.LG 57%

A lightweight hybrid CNN-LSTM model for ECG-based arrhythmia detection

Negin Alamatsaz, Leyla s Tabatabaei, Mohammadreza Yazdchi, Hamidreza Payan, Nima Alamatsaz, Fahimeh Nasimi

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

Comments 7 pages, 4 figures, 3 tables

2208.14543 2022-09-01 cs.RO cs.CV cs.LG 57%

BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognition

Peng Yin, Abulikemu Abuduweili, Shiqi Zhao, Changliu Liu, Sebastian Scherer

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 19 pages, 18 figures, submitted to IEEE T-RO

2205.03530 2022-08-31 cs.AI cs.CY cs.SI 57%

Gigs with Guarantees: Achieving Fair Wage for Food Delivery Workers

Ashish Nair, Rahul Yadav, Anjali Gupta, Abhijnan Chakraborty, Sayan Ranu, Amitabha Bagchi

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Appeared in International Joint Conference on Artificial Intelligence (IJCAI) 2022

2105.05155 2022-08-31 cs.LG 57%

TAG: Task-based Accumulated Gradients for Lifelong learning

Pranshu Malviya, Balaraman Ravindran, Sarath Chandar

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Published at 1st Conference on Lifelong Learning Agents, 2022

2208.12191 2022-08-26 cs.LG math.OC 57%

Turning Mathematics Problems into Games: Reinforcement Learning and Gröbner bases together solve Integer Feasibility Problems

Yue Wu, Jesús A. De Loera

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1808.02932 2022-08-26 stat.ML cs.LG stat.CO 57%

Nonparametric Gaussian Mixture Models for the Multi-Armed Bandit

Iñigo Urteaga, Chris H. Wiggins

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments The software used for this study is publicly available at https://github.com/iurteaga/bandits

2204.00755 2022-08-24 cs.AI 57%

Safe Reinforcement Learning via Shielding under Partial Observability

Steven Carr, Nils Jansen, Sebastian Junges, Ufuk Topcu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 21 pages, 28 Figures, 3 Tables

2208.09367 2022-08-22 cs.CL cs.HC 57%

Dialogue Policies for Confusion Mitigation in Situated HRI

Na Li, Robert Ross

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments 2pages, 1figure, 1 page literture, Semdial2022 Conference (https://semdial2022.github.io/?page=program#)

2208.04273 2022-08-15 cs.AI 57%

Improving performance in multi-objective decision-making in Bottles environments with soft maximin approaches

Benjamin J Smith, Robert Klassert, Roland Pihlakas

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2203.08222 2022-08-09 cs.LG 57%

Zipfian environments for Reinforcement Learning

Stephanie C. Y. Chan, Andrew K. Lampinen, Pierre H. Richemond, Felix Hill

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2208.00737 2022-08-02 cs.MA cs.AI cs.PL 57%

e-Genia3 An AgentSpeak extension for empathic agents

Joaquin Taverner, Emilio Vivancos, Vicente Botti

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2208.00383 2022-08-02 cs.NI cs.AI 57%

DRL-M4MR: An Intelligent Multicast Routing Approach Based on DQN Deep Reinforcement Learning in SDN

Chenwei Zhao, Miao Ye, Xingsi Xue, Jianhui Lv, Qiuxiang Jiang, Yong Wang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2106.14956 2022-07-27 math.OC cs.DC cs.LG stat.ML 57%

Robust Distributed Optimization With Randomly Corrupted Gradients

Berkay Turan, Cesar A. Uribe, Hoi-To Wai, Mahnoosh Alizadeh

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 21 pages, 5 figures

2110.12352 2022-07-27 cs.RO cs.AI 57%

DiffSRL: Learning Dynamical State Representation for Deformable Object Manipulation with Differentiable Simulator

Sirui Chen, Yunhao Liu, Jialong Li, Shang Wen Yao, Tingxiang Fan, Jia Pan

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

Comments 8 pages 9 figures

Journal ref IEEE Robotics and Automation Letters, 2022

2202.00850 2022-07-26 cs.CV cs.LG cs.SD eess.AS eess.IV 57%

Active Audio-Visual Separation of Dynamic Sound Sources

Sagnik Majumder, Kristen Grauman

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted to ECCV 2022

2110.03267 2022-07-13 cs.RO cs.CV cs.LG 57%

Propagating State Uncertainty Through Trajectory Forecasting

Boris Ivanovic, Yifeng Lin, Shubham Shrivastava, Punarjay Chakravarty, Marco Pavone

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

Comments IEEE International Conference on Robotics and Automation (ICRA) 2022 -- 8 pages, 6 figures, 4 tables

1. 记忆与上下文管理 4758 篇

A Unified Algorithm for Stochastic Path Problems

Few-Shot Continual Active Learning by a Robot

Near-Optimal Randomized Exploration for Tabular Markov Decision Processes

From Eye-blinks to State Construction: Diagnostic Benchmarks for Online Representation Learning

DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning

Tractable Optimality in Episodic Latent MABs

Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use case

S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees

A Case Report On The "A.I. Locked-In Problem": social concerns with modern NLP

ProAPT: Projection of APT Threats with Deep Reinforcement Learning

Self-supervised Sequential Information Bottleneck for Robust Exploration in Deep Reinforcement Learning

Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees

Project proposal: A modular reinforcement learning based automated theorem prover

A lightweight hybrid CNN-LSTM model for ECG-based arrhythmia detection

BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognition

Gigs with Guarantees: Achieving Fair Wage for Food Delivery Workers

TAG: Task-based Accumulated Gradients for Lifelong learning

Turning Mathematics Problems into Games: Reinforcement Learning and Gröbner bases together solve Integer Feasibility Problems

Nonparametric Gaussian Mixture Models for the Multi-Armed Bandit

Safe Reinforcement Learning via Shielding under Partial Observability

Dialogue Policies for Confusion Mitigation in Situated HRI

Improving performance in multi-objective decision-making in Bottles environments with soft maximin approaches

Zipfian environments for Reinforcement Learning

e-Genia3 An AgentSpeak extension for empathic agents

DRL-M4MR: An Intelligent Multicast Routing Approach Based on DQN Deep Reinforcement Learning in SDN

Robust Distributed Optimization With Randomly Corrupted Gradients

DiffSRL: Learning Dynamical State Representation for Deformable Object Manipulation with Differentiable Simulator

Active Audio-Visual Separation of Dynamic Sound Sources

Propagating State Uncertainty Through Trajectory Forecasting