AI Agent - arXivDaily 专题

2012.13658 2021-06-15 cs.LG 57%

Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards

Susan Amin, Maziar Gomrokchi, Hossein Aboutalebi, Harsh Satija, Doina Precup

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments To be published in ICML, 2021

2106.03050 2021-06-08 cs.LG 57%

Efficient Continuous Control with Double Actors and Regularized Critics

Jiafei Lyu, Xiaoteng Ma, Jiangpeng Yan, Xiu Li

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 21 pages

2106.02396 2021-06-07 eess.SY cs.LG cs.SY 57%

A Learning-based Optimal Market Bidding Strategy for Price-Maker Energy Storage

Mathilde D. Badoual, Scott J. Moura

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Presented at the 2021 American Control Conference (ACC), New Orleans, USA, May 25-28, 2021

2106.02204 2021-06-07 cs.AI 57%

Detecting and Adapting to Novelty in Games

Xiangyu Peng, Jonathan C. Balloch, Mark O. Riedl

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 10 pages, 5 figures, Accepted to the AAAI21 Workshop on on Reinforcement Learning in Games

2102.13565 2021-06-07 cs.LG 57%

Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision

Johan Bjorck, Xiangyu Chen, Christopher De Sa, Carla P. Gomes, Kilian Q. Weinberger

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2105.09992 2021-06-01 cs.LG 57%

Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness

Mathieu Seurin, Florian Strub, Philippe Preux, Olivier Pietquin

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted at Internationnal Joint Conference on Artificial Intelligence (IJCAI'21) and Self-Supervision for Reinforcement Learning Workshop (SSL-RL @ICLR'21)

2006.13912 2021-06-01 math.OC cs.LG cs.MA 57%

Unified Reinforcement Q-Learning for Mean Field Game and Control Problems

Andrea Angiuli, Jean-Pierre Fouque, Mathieu Laurière

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2105.10577 2021-05-25 cs.AI cs.NE 57%

Modelling the development of counting with memory-augmented neural networks

Zack Dulberg, Taylor Webb, Jonathan Cohen

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Accepted talk at Proceedings of the 42nd Annual Meeting of the Cognitive Science Society

2105.07284 2021-05-24 q-bio.NC cs.AI 57%

A brain basis of dynamical intelligence for AI and computational neuroscience

Joseph D. Monaco, Kanaka Rajan, Grace M. Hwang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Perspective article: 24 pages, 3 figures, 1 display box

2105.09059 2021-05-20 cs.CY cs.AI 57%

The State of AI Ethics Report (January 2021)

Abhishek Gupta, Alexandrine Royer, Connor Wright, Falaah Arif Khan, Victoria Heath, Erick Galinkin, Ryan Khurana, Marianna Bergamaschi Ganapini, Muriam Fancy, Masa Sweidan, Mo Akif, Renjie Butalid

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

Comments 188 pages

2101.09536 2021-05-07 cs.CV cs.LG 57%

Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer

James Smith, Jonathan Balloch, Yen-Chang Hsu, Zsolt Kira

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted by the 2021 International Joint Conference on Neural Networks (IJCNN 2021)

2007.04546 2021-04-26 cs.LG cs.CV stat.ML 57%

Wandering Within a World: Online Contextualized Few-Shot Learning

Mengye Ren, Michael L. Iuzzolino, Michael C. Mozer, Richard S. Zemel

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments ICLR 2021

2104.08060 2021-04-19 cs.LG 57%

MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks

Danilo Numeroso, Davide Bacciu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 8 pages, 5 figures, to appear in the Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN 2021)

2104.02899 2021-04-08 cs.LG 57%

Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units

Ankur Mali, Alexander Ororbia, Daniel Kifer, C. Lee Giles

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2104.00249 2021-04-02 cs.CV cs.LG 57%

LaPred: Lane-Aware Prediction of Multi-Modal Future Trajectories of Dynamic Agents

ByeoungDo Kim, Seong Hyeon Park, Seokhwan Lee, Elbek Khoshimjonov, Dongsuk Kum, Junsoo Kim, Jeong Soo Kim, Jun Won Choi

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 13 pages, 2 figures, 7 tables, CVPR 2021

2103.14251 2021-03-29 eess.SY cs.LG cs.SY physics.soc-ph 57%

Embedding Power Flow into Machine Learning for Parameter and State Estimation

Laurent Pagnier, Michael Chertkov

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

Comments 7 pages, 3 figures, 1 table

2011.01834 2021-03-29 cs.SE 57%

Reinforcement Learning for Test Case Prioritization

Mojtaba Bagherzadeh, Nafiseh Kahani, Lionel Briand

专题命中记忆与上下文管理：agent(abstract)；分类 cs.SE

Journal ref IEEE Transactions on Software Engineering (TSE). (2021) 1-21

2006.04678 2021-03-18 cs.LG stat.ML 57%

Primal Wasserstein Imitation Learning

Robert Dadashi, Léonard Hussenot, Matthieu Geist, Olivier Pietquin

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Published in International Conference on Learning Representations (ICLR 2021)

2006.10178 2021-03-16 stat.ML cs.CV cs.LG 57%

Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF

Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt, Justin Bayer

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

Comments Update for ICLR2021

2103.08107 2021-03-16 cs.LG 57%

Mutual Information State Intrinsic Control

Rui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp, Wei Xu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Published in International Conference on Learning Representations (ICLR 2021) as Spotlight (top 5%), Link: https://openreview.net/forum?id=OthEq8I5v1. arXiv admin note: text overlap with arXiv:2002.01963

2103.08079 2021-03-16 cs.HC cs.AI cs.RO 57%

Crossing the Tepper Line: An Emerging Ontology for Describing the Dynamic Sociality of Embodied AI

Katie Seaborn, Peter Pennefather, Norihisa P. Miyake, Mihoko Otake-Matsuura

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

Comments Accepted at CHI EA '21

2103.06371 2021-03-12 cs.AI 57%

Hard Attention Control By Mutual Information Maximization

Himanshu Sahni, Charles Isbell

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2008.13319 2021-03-11 cs.LG stat.ML 57%

Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL

Xiaoyu Chen, Jiachen Hu, Lihong Li, Liwei Wang

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

2103.04152 2021-03-09 eess.SY cs.LG cs.SY 57%

Correlated Deep Q-learning based Microgrid Energy Management

Hao Zhou, Melike Erol-Kantarci

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2008.06036 2021-03-08 cs.LG stat.ML 57%

Reinforcement Learning with Trajectory Feedback

Yonathan Efroni, Nadav Merlis, Shie Mannor

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments AAAI2021

2002.07717 2021-03-02 stat.ML cs.LG 57%

Reinforcement Learning for Molecular Design Guided by Quantum Mechanics

Gregor N. C. Simm, Robert Pinsler, José Miguel Hernández-Lobato

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Journal ref Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020

2102.12425 2021-02-25 cs.LG 57%

Synthetic Returns for Long-Term Credit Assignment

David Raposo, Sam Ritter, Adam Santoro, Greg Wayne, Theophane Weber, Matt Botvinick, Hado van Hasselt, Francis Song

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1911.07643 2021-02-18 cs.LG stat.ML 57%

Influence-aware Memory Architectures for Deep Reinforcement Learning

Miguel Suau, Jinke He, Elena Congeduti, Rolf A. N. Starre, Aleksander Czechowski, Frans A. Oliehoek

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2102.07599 2021-02-16 cs.AI 57%

Seeing by haptic glance: reinforcement learning-based 3D object Recognition

Kevin Riou, Suiyi Ling, Guillaume Gallot, Patrick Le Callet

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 5 pages

1903.07097 2021-02-16 cs.DB cs.LG 57%

tspDB: Time Series Predict DB

Anish Agarwal, Abdullah Alomar, Devavrat Shah

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

1. 记忆与上下文管理 4793 篇

Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards

Efficient Continuous Control with Double Actors and Regularized Critics

A Learning-based Optimal Market Bidding Strategy for Price-Maker Energy Storage

Detecting and Adapting to Novelty in Games

Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision

Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness

Unified Reinforcement Q-Learning for Mean Field Game and Control Problems

Modelling the development of counting with memory-augmented neural networks

A brain basis of dynamical intelligence for AI and computational neuroscience

The State of AI Ethics Report (January 2021)

Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer

Wandering Within a World: Online Contextualized Few-Shot Learning

MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks

Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units

LaPred: Lane-Aware Prediction of Multi-Modal Future Trajectories of Dynamic Agents

Embedding Power Flow into Machine Learning for Parameter and State Estimation

Reinforcement Learning for Test Case Prioritization

Primal Wasserstein Imitation Learning

Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF

Mutual Information State Intrinsic Control

Crossing the Tepper Line: An Emerging Ontology for Describing the Dynamic Sociality of Embodied AI

Hard Attention Control By Mutual Information Maximization

Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL

Correlated Deep Q-learning based Microgrid Energy Management

Reinforcement Learning with Trajectory Feedback

Reinforcement Learning for Molecular Design Guided by Quantum Mechanics

Synthetic Returns for Long-Term Credit Assignment

Influence-aware Memory Architectures for Deep Reinforcement Learning

Seeing by haptic glance: reinforcement learning-based 3D object Recognition

tspDB: Time Series Predict DB