AI Agent - arXivDaily 专题

2303.07798 2023-03-15 cs.CV cs.AI 57%

OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav

Karmesh Yadav, Arjun Majumdar, Ram Ramrakhya, Naoki Yokoyama, Alexei Baevski, Zsolt Kira, Oleksandr Maksymets, Dhruv Batra

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

Comments 15 pages, 7 figures, 9 tables

2303.05710 2023-03-13 cs.DB cs.LG 57%

A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning

Xinyi Zhang, Zhuo Chang, Hong Wu, Yang Li, Jia Chen, Jian Tan, Feifei Li, Bin Cui

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted at 2023 International Conference on Management of Data (SIGMOD '23)

2303.03068 2023-03-07 cs.LG 57%

Reinforcement Learning Based Self-play and State Stacking Techniques for Noisy Air Combat Environment

Ahmet Semih Tasbas, Safa Onur Sahin, Nazim Kemal Ure

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 10 pages, 4 figures

2302.14803 2023-03-01 cs.RO cs.LG 57%

Learned Risk Metric Maps for Kinodynamic Systems

Ross Allen, Wei Xiao, Daniela Rus

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2207.12763 2023-03-01 cs.AI 57%

Using Abstraction for Interpretable Robot Programs in Stochastic Domains

Till Hofmann, Vaishak Belle

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Presented at the KR'22 Workshop on Explainable Logic-Based Knowledge Representation (XLoKR). arXiv admin note: substantial text overlap with arXiv:2204.03536

2302.12107 2023-02-24 cs.GT cs.AI cs.MA math.DS 57%

Single-Peaked Jump Schelling Games

Tobias Friedrich, Pascal Lenzner, Louise Molitor, Lars Seifert

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2302.09424 2023-02-21 cs.CL 57%

Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation

Mehrad Moradshahi, Sina J. Semnani, Monica S. Lam

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments Published in EACL 2023

2302.08600 2023-02-20 cs.DC cs.AI cs.MA 57%

On the Role of Memory in Robust Opinion Dynamics

Luca Becchetti, Andrea Clementi, Amos Korman, Francesco Pasquale, Luca Trevisan, Robin Vacus

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2302.04856 2023-02-10 cs.RO cs.CV cs.LG 57%

One-shot Visual Imitation via Attributed Waypoints and Demonstration Augmentation

Matthew Chang, Saurabh Gupta

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Project Page: https://matthewchang.github.io/awda_site

2212.11709 2023-02-10 eess.SY cs.IR cs.LG cs.PF cs.SY 57%

Reinforcement Learning Based Approaches to Adaptive Context Caching in Distributed Context Management Systems

Shakthi Weerasinghe, Arkady Zaslavsky, Seng W. Loke, Amin Abken, Alireza Hassani

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments This is a pre-print version of the journal paper submitted to ACM Transactions in Internet of Things, which is currently under review

2302.04125 2023-02-09 cs.LG 57%

Intrinsic Rewards from Self-Organizing Feature Maps for Exploration in Reinforcement Learning

Marius Lindegaard, Hjalmar Jacob Vinje, Odin Aleksander Severinsen

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 10 pages, 4 figures. Code publicly available at https://github.com/mariuslindegaard/curiosity_baselines

2302.03816 2023-02-09 cs.AI 57%

Intend-Wait-Perceive-Cross: Exploring the Effects of Perceptual Limitations on Pedestrian Decision-Making

Iuliia Kotseruba, Amir Rasouli

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 6 pages, 5 figures, 2 tables

2301.13556 2023-02-01 cs.AI 57%

Purposeful and Operation-based Cognitive System for AGI

Shimon Komarovsky

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2301.07345 2023-01-19 cs.AI 57%

Implicit State and Goals in QBF Encodings for Positional Games (extended version)

Irfansha Shaik, Valentin Mayer-Eichberger, Jaco van de Pol, Abdallah Saffidine

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

Comments 11 pages (including appendix), 5 figures and 4 tables

2204.01467 2023-01-18 cs.CY cs.LG physics.chem-ph 57%

On scientific understanding with artificial intelligence

Mario Krenn, Robert Pollice, Si Yue Guo, Matteo Aldeghi, Alba Cervera-Lierta, Pascal Friederich, Gabriel dos Passos Gomes, Florian Häse, Adrian Jinich, AkshatKumar Nigam, Zhenpeng Yao, Alán Aspuru-Guzik

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 13 pages, 3 figures, comments welcome!

Journal ref Nature Review Physics 4, 761 (2022)

2301.02561 2023-01-09 cs.RO cs.AI 57%

Multi-Vehicle Trajectory Prediction at Intersections using State and Intention Information

Dekai Zhu, Qadeer Khan, Daniel Cremers

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2101.05181 2023-01-06 cs.CV cs.AI cs.RO 57%

Memory-Augmented Reinforcement Learning for Image-Goal Navigation

Lina Mezghani, Sainbayar Sukhbaatar, Thibaut Lavril, Oleksandr Maksymets, Dhruv Batra, Piotr Bojanowski, Karteek Alahari

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Journal ref IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022

2212.10346 2022-12-21 cs.RO cs.CL 57%

Does It Affect You? Social and Learning Implications of Using Cognitive-Affective State Recognition for Proactive Human-Robot Tutoring

Matthias Kraus, Diana Betancourt, Wolfgang Minker

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

2212.08481 2022-12-19 cs.LG cs.CY q-bio.PE 57%

Neural Network Augmented Compartmental Pandemic Models

Lorenz Kummer, Kevin Sidak

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 13 pages, 19 figures

2212.04606 2022-12-12 quant-ph cs.LG 57%

The R-algebra of Quasiknowledge and Convex Optimization

Duyal Yolcu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 40 pages

2212.02988 2022-12-07 cs.LG cs.CV cs.RO stat.ML 57%

PRISM: Probabilistic Real-Time Inference in Spatial World Models

Atanas Mirchev, Baris Kayalibay, Ahmed Agha, Patrick van der Smagt, Daniel Cremers, Justin Bayer

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Will appear in PMLR, CoRL 2022

2212.01838 2022-12-06 cs.LG cs.LO 57%

Automata Learning meets Shielding

Martin Tappler, Stefan Pranger, Bettina Könighofer, Edi Muškardin, Roderick Bloem, Kim Larsen

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2212.00389 2022-12-02 cs.RO cs.AI 57%

Kick-motion Training with DQN in AI Soccer Environment

Bumgeun Park, Jihui Lee, Taeyoung Kim, Dongsoo Har

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 4 pages, 4 figures

2211.12930 2022-11-24 cs.RO cs.AI 57%

Introspection-based Explainable Reinforcement Learning in Episodic and Non-episodic Scenarios

Niclas Schroeter, Francisco Cruz, Stefan Wermter

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2211.11620 2022-11-22 cs.LG 57%

Simultaneously Updating All Persistence Values in Reinforcement Learning

Luca Sabbioni, Luca Al Daire, Lorenzo Bisi, Alberto Maria Metelli, Marcello Restelli

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1912.13309 2022-11-11 eess.SY cs.LG cs.SY math.OC 57%

Learning in Discounted-cost and Average-cost Mean-field Games

Berkay Anahtarcı, Can Deha Karıksız, Naci Saldi

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 59 pages

2201.08610 2022-11-08 cs.LG 57%

Deep Q-learning: a robust control approach

Balazs Varga, Balazs Kulcsar, Morteza Haghir Chehreghani

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Journal ref Int J Robust Nonlinear Control. 2022; 1- 19

2210.12521 2022-10-25 cs.RO cs.AI cs.CV 57%

H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions

Kei Ota, Hsiao-Yu Tung, Kevin A. Smith, Anoop Cherian, Tim K. Marks, Alan Sullivan, Asako Kanezaki, Joshua B. Tenenbaum

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

2203.09251 2022-10-25 cs.LG stat.ML 57%

Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs

Andrea Tirinzoni, Aymen Al-Marjani, Emilie Kaufmann

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2210.09636 2022-10-19 eess.SP cs.LG cs.RO 57%

Split-KalmanNet: A Robust Model-Based Deep Learning Approach for SLAM

Geon Choi, Jeonghun Park, Nir Shlezinger, Yonina C. Eldar, Namyoon Lee

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 6 pages, 6 figures

1. 记忆与上下文管理 4758 篇

OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav

A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning

Reinforcement Learning Based Self-play and State Stacking Techniques for Noisy Air Combat Environment

Learned Risk Metric Maps for Kinodynamic Systems

Using Abstraction for Interpretable Robot Programs in Stochastic Domains

Single-Peaked Jump Schelling Games

Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation

On the Role of Memory in Robust Opinion Dynamics

One-shot Visual Imitation via Attributed Waypoints and Demonstration Augmentation

Reinforcement Learning Based Approaches to Adaptive Context Caching in Distributed Context Management Systems

Intrinsic Rewards from Self-Organizing Feature Maps for Exploration in Reinforcement Learning

Intend-Wait-Perceive-Cross: Exploring the Effects of Perceptual Limitations on Pedestrian Decision-Making

Purposeful and Operation-based Cognitive System for AGI

Implicit State and Goals in QBF Encodings for Positional Games (extended version)

On scientific understanding with artificial intelligence

Multi-Vehicle Trajectory Prediction at Intersections using State and Intention Information

Memory-Augmented Reinforcement Learning for Image-Goal Navigation

Does It Affect You? Social and Learning Implications of Using Cognitive-Affective State Recognition for Proactive Human-Robot Tutoring

Neural Network Augmented Compartmental Pandemic Models

The R-algebra of Quasiknowledge and Convex Optimization

PRISM: Probabilistic Real-Time Inference in Spatial World Models

Automata Learning meets Shielding

Kick-motion Training with DQN in AI Soccer Environment

Introspection-based Explainable Reinforcement Learning in Episodic and Non-episodic Scenarios

Simultaneously Updating All Persistence Values in Reinforcement Learning

Learning in Discounted-cost and Average-cost Mean-field Games

Deep Q-learning: a robust control approach

H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions

Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs

Split-KalmanNet: A Robust Model-Based Deep Learning Approach for SLAM