AI Agent - arXivDaily 专题

2201.06953 2022-01-19 cs.CY cs.AI cs.LG 62%

Knowledge Tracing: A Survey

Ghodai Abdelrahman, Qing Wang, Bernardo Pereira Nunes

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2201.06348 2022-01-19 cs.CL cs.AI 62%

Chatbot System Architecture

Moataz Mohammed, Mostafa M. Aref

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.CL

2111.00876 2022-01-19 cs.LG cs.AI 62%

On the Expressivity of Markov Reward

David Abel, Will Dabney, Anna Harutyunyan, Mark K. Ho, Michael L. Littman, Doina Precup, Satinder Singh

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted to NeurIPS 2021

2201.04866 2022-01-14 cs.CV cs.AI cs.LG 62%

Weakly Supervised Scene Text Detection using Deep Reinforcement Learning

Emanuel Metzenthin, Christian Bartz, Christoph Meinel

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2111.02056 2022-01-13 cs.LG cs.AI 62%

Curriculum Offline Imitation Learning

Minghuan Liu, Hanye Zhao, Zhengyu Yang, Jian Shen, Weinan Zhang, Li Zhao, Tie-Yan Liu

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 19 pages (7 pages of supplementary), 11 figures. Published at 35th Conference on Neural Information Processing Systems (NeurIPS 2021)

2112.15430 2022-01-03 cs.LG cs.AI math.OC 62%

Robustness and risk management via distributional dynamic programming

Mastane Achab, Gergely Neu

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2111.01201 2022-01-03 cs.LG cs.AI cs.GT cs.SY eess.SY 62%

Unintended Selection: Persistent Qualification Rate Disparities and Interventions

Reilly Raab, Yang Liu

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 39 pages, 10 figures, to be published in the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)

2112.14705 2021-12-30 cs.RO cs.AI cs.LG 62%

Lane Change Decision-Making through Deep Reinforcement Learning

Mukesh Ghimire, Malobika Roy Choudhury, Guna Sekhar Sai Harsha Lagudu

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 6 pages

2110.07700 2021-12-17 cs.LG cs.AI 62%

Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units

Kenny Young

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments To be presented at AAAI 2022

2106.03035 2021-12-17 q-fin.TR cs.AI cs.LG 62%

Online Trading Models with Deep Reinforcement Learning in the Forex Market Considering Transaction Costs

Koya Ishikawa, Kazuhide Nakata

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 7 pages, 2 figures, 6 tables

2112.07263 2021-12-15 cs.LG cs.AI 62%

Quantifying Multimodality in World Models

Andreas Sedlmeier, Michael Kölle, Robert Müller, Leo Baudrexel, Claudia Linnhoff-Popien

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2112.06628 2021-12-15 quant-ph cs.AI cs.LG 62%

Quantum Stream Learning

Yongcheng Ding, Xi Chen, Rafael Magdalena-Benedicto, José D. Martín-Guerrero

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 7 pages, 3 figures, submitted to the special issue on stream learning, comments are welcomed

2112.06511 2021-12-14 cs.LG cs.AI cs.CV 62%

Ex-Model: Continual Learning from a Stream of Trained Models

Antonio Carta, Andrea Cossu, Vincenzo Lomonaco, Davide Bacciu

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2109.07263 2021-12-08 cs.CL cs.LG 62%

End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

Dinesh Raghu, Shantanu Agarwal, Sachindra Joshi, Mausam

专题命中 Agent评测：agent(abstract)；分类 cs.CL、cs.LG

Comments This is a Post-EMNLP Version that contains results on the new hidden test set. D.Raghu and S.Agarwal contributed equally to this work

2112.01537 2021-12-07 cs.HC cs.AI cs.LG 62%

Improving mathematical questioning in teacher training

Debajyoti Datta, Maria Phillips, James P Bywater, Jennifer Chiu, Ginger S. Watson, Laura E. Barnes, Donald E Brown

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted to appear at the NeurIPS 2021 Human Centered AI Workshop (HCAI). Data collection process for this data is described here arXiv:2112.00985

2112.01603 2021-12-06 cs.AI cs.LG 62%

Neurosymbolic Systems of Perception & Cognition: The Role of Attention

Hugo Latapie, Ozkan Kilic, Kristinn R. Thorisson, Pei Wang, Patrick Hammer

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2112.00985 2021-12-03 cs.AI cs.HC cs.LG 62%

Evaluation of mathematical questioning strategies using data collected through weak supervision

Debajyoti Datta, Maria Phillips, James P Bywater, Jennifer Chiu, Ginger S. Watson, Laura E. Barnes, Donald E Brown

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted to appear at the NeurIPS 2021 Workshop on Math AI for Education (MATHAI4ED)

2112.00979 2021-12-03 cs.LG cs.AI 62%

Recommending with Recommendations

Naveen Durvasula, Franklyn Wang, Scott Duke Kominers

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 22 pages, 2 figures

2112.00579 2021-12-02 cs.LG cs.AI cs.CY cs.MA 62%

Conditional Expectation based Value Decomposition for Scalable On-Demand Ride Pooling

Avinandan Bose, Pradeep Varakantham

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Preprint. Under Review. arXiv admin note: text overlap with arXiv:1911.08842

2112.00478 2021-12-02 cs.LG cs.AI stat.ML 62%

On the Practical Consistency of Meta-Reinforcement Learning Algorithms

Zheng Xiong, Luisa Zintgraf, Jacob Beck, Risto Vuorio, Shimon Whiteson

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2111.14629 2021-11-30 cs.LG cs.AI 62%

Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions

Bogdan Mazoure, Ilya Kostrikov, Ofir Nachum, Jonathan Tompson

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Offline RL workshop at NeurIPS 2021

2111.12861 2021-11-29 cs.LG cs.AI cs.CY 62%

A Deep Learning Approach for Macroscopic Energy Consumption Prediction with Microscopic Quality for Electric Vehicles

Ayman Moawad, Krishna Murthy Gurumurthy, Omer Verbas, Zhijian Li, Ehsan Islam, Vincent Freyermuth, Aymeric Rousseau

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 12 pages, 16 figures. arXiv admin note: text overlap with arXiv:2110.10887

2103.06859 2021-11-29 cs.LG cs.AI 62%

Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control

Beren Millidge, Anil Seth, Christopher Buckley

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 11-03-21 initial upload. 14-03-21 fix Charnov citation. 16-03-21 another fix. 25-06-21 more fixes plus numerical simulations. 30-06-21 minor fixes; 12/11/21 maths typo fix; 24/11/21 minor maths fixes

2111.11576 2021-11-26 cs.LG cs.CL cs.CV 62%

Building Goal-Oriented Dialogue Systems with Situated Visual Context

Sanchit Agarwal, Jan Jezabek, Arijit Biswas, Emre Barut, Shuyang Gao, Tagyoung Chung

专题命中 Agent评测：agent(abstract)；分类 cs.CL、cs.LG

2111.11964 2021-11-24 cs.LG cs.AI cs.NE 62%

Reviewing continual learning from the perspective of human-level intelligence

Yifan Chang, Wenbo Li, Jian Peng, Bo Tang, Yu Kang, Yinjie Lei, Yuanmiao Gui, Qing Zhu, Yu Liu, Haifeng Li

专题命中 Agent评测：AI agent(abstract)；分类 cs.AI、cs.LG

Comments 21 pages, 10 figures

2111.11363 2021-11-23 cs.CL cs.AI 62%

DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation

Jing Yang Lee, Kong Aik Lee, Woon Seng Gan

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.CL

Comments Accepted at ICAART 2022 as Full Paper

2111.11212 2021-11-23 cs.LG cs.AI 62%

Finding Useful Predictions by Meta-gradient Descent to Improve Decision-making

Alex Kearney, Anna Koop, Johannes Günther, Patrick M. Pilarski

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Journal ref NeurIPS 2021 Workshop on Self-Supervised Learning: Theory and Practice

2111.08458 2021-11-17 cs.LG cs.AI 62%

Lifelong Learning from Event-based Data

Vadym Gryshchuk, Cornelius Weber, Chu Kiong Loo, Stefan Wermter

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments In Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

2107.04457 2021-11-17 cs.RO cs.AI cs.LG physics.optics 62%

Aligning an optical interferometer with beam divergence control and continuous action space

Stepan Makarenko, Dmitry Sorokin, Alexander Ulanov, A. I. Lvovsky

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 12 pages, 5 figures

1910.07294 2021-11-12 cs.LG cs.AI cs.RO stat.ML 62%

Reinforcement Learning for Robotic Manipulation using Simulated Locomotion Demonstrations

Ozsel Kilinc, Giovanni Montana

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments To appear in ECML PKDD 2022

1. Agent评测 15801 篇

Knowledge Tracing: A Survey

Chatbot System Architecture

On the Expressivity of Markov Reward

Weakly Supervised Scene Text Detection using Deep Reinforcement Learning

Curriculum Offline Imitation Learning

Robustness and risk management via distributional dynamic programming

Unintended Selection: Persistent Qualification Rate Disparities and Interventions

Lane Change Decision-Making through Deep Reinforcement Learning

Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units

Online Trading Models with Deep Reinforcement Learning in the Forex Market Considering Transaction Costs

Quantifying Multimodality in World Models

Quantum Stream Learning

Ex-Model: Continual Learning from a Stream of Trained Models

End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

Improving mathematical questioning in teacher training

Neurosymbolic Systems of Perception & Cognition: The Role of Attention

Evaluation of mathematical questioning strategies using data collected through weak supervision

Recommending with Recommendations

Conditional Expectation based Value Decomposition for Scalable On-Demand Ride Pooling

On the Practical Consistency of Meta-Reinforcement Learning Algorithms

Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions

A Deep Learning Approach for Macroscopic Energy Consumption Prediction with Microscopic Quality for Electric Vehicles

Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control

Building Goal-Oriented Dialogue Systems with Situated Visual Context

Reviewing continual learning from the perspective of human-level intelligence

DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation

Finding Useful Predictions by Meta-gradient Descent to Improve Decision-making

Lifelong Learning from Event-based Data

Aligning an optical interferometer with beam divergence control and continuous action space

Reinforcement Learning for Robotic Manipulation using Simulated Locomotion Demonstrations