AI Agent - arXivDaily 专题

2211.07369 2022-11-15 cs.LG 57%

A deep learning framework to generate realistic population and mobility data

Eren Arkangil, Mehmet Yildirimoglu, Jiwon Kim, Carlo Prato

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2211.06883 2022-11-15 cs.LG stat.ML 57%

Generalizing distribution of partial rewards for multi-armed bandits with temporally-partitioned rewards

Ronald C. van den Broek, Rik Litjens, Tobias Sagis, Luc Siecker, Nina Verbeeke, Pratik Gajane

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2211.06429 2022-11-15 cs.SE 57%

Evaluation of tools for describing, reproducing and reusing scientific workflows

Philipp Diercks, Dennis Gläser, Ontje Lünsdorf, Michael Selzer, Bernd Flemisch, Jörg F. Unger

专题命中 Agent评测：workflow(abstract)；分类 cs.SE

2202.08137 2022-11-14 cs.LG 57%

A data-driven approach for learning to control computers

Peter C Humphreys, David Raposo, Toby Pohlen, Gregory Thornton, Rachita Chhaparia, Alistair Muldal, Josh Abramson, Petko Georgiev, Alex Goldin, Adam Santoro, Timothy Lillicrap

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Journal ref Proceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022

2211.05338 2022-11-11 cs.DC cs.LG 57%

Job Scheduling in Datacenters using Constraint Controlled RL

Vanamala Venkataswamy

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments under submission

2211.01991 2022-11-11 cs.RO cs.LG 57%

Leveraging Fully Observable Policies for Learning under Partial Observability

Hai Nguyen, Andrea Baisero, Dian Wang, Christopher Amato, Robert Platt

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Accepted at the 2022 Conference on Robot Learning (CoRL), Auckland, New Zealand

2206.11812 2022-11-10 cs.AI 57%

Formalizing the Problem of Side Effect Regularization

Alexander Matt Turner, Aseem Saxena, Prasad Tadepalli

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 14 pages, accepted to ML Safety Workshop at NeurIPS 2022. Alexander Turner and Aseem Saxena contributed equally

2211.04327 2022-11-09 cs.LG cs.CE 57%

Synthesis of separation processes with reinforcement learning

Stephan C. P. A. van Kalmthout, Laurence I. Midgley, Meik B. Franke

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2211.04056 2022-11-09 cs.HC cs.AI 57%

Stress Propagation in Human-Robot Teams Based on Computational Logic Model

Peter Shmerko, Yumi Iwashita, Adrian Stoica, Svetlana Yanushkevich

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments Submitted to IEEE Aerospace 2023 conference

2205.12113 2022-11-09 cs.CL 57%

The Curious Case of Control

Elias Stengel-Eskin, Benjamin Van Durme

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments EMNLP 2022

2210.15099 2022-11-08 cs.RO cs.HC cs.LG 57%

Coordination with Humans via Strategy Matching

Michelle Zhao, Reid Simmons, Henny Admoni

专题命中 Agent评测：agent(abstract)；分类 cs.LG

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

2211.03049 2022-11-08 cs.RO cs.AI q-bio.NC 57%

Learning body models: from humans to humanoids

Matej Hoffmann

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 34 pages, 5 figures. Habilitation thesis, Faculty of Electrical Engineering, Czech Technical University in Prague (2021)

2010.09325 2022-11-08 q-bio.NC cs.AI 57%

Body models in humans, animals, and robots: mechanisms and plasticity

Matej Hoffmann

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 27 pages, 8 figures

Journal ref 2021, Body Schema and Body Image: New Directions, Oxford University Press, pp. 152-180

2004.09677 2022-11-07 cs.LG stat.ML 57%

Approximate exploitability: Learning a best response in large games

Finbarr Timbers, Nolan Bard, Edward Lockhart, Marc Lanctot, Martin Schmid, Neil Burch, Julian Schrittwieser, Thomas Hubert, Michael Bowling

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2111.03699 2022-11-04 cs.AI cs.IT cs.SY eess.SY math.IT 57%

A space of goals: the cognitive geometry of informationally bounded agents

Karen Archer, Nicola Catenacci Volpi, Franziska Bröker, Daniel Polani

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments Includes supplementary material, 6 figures in the main document, 5 figures in the supplementary material. Replacing preprint with author accepted manuscript

2203.08207 2022-11-01 cs.CV cs.LG 57%

SocialVAE: Human Trajectory Prediction using Timewise Latents

Pei Xu, Jean-Bernard Hayet, Ioannis Karamouzas

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments In the 17th European Conference on Computer Vision (ECCV 2022). Code: https://github.com/xupei0610/SocialVAE

Journal ref Computer Vision -- ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13664, page 511--528

2210.15449 2022-10-28 cs.RO cs.AI 57%

Conditional Goal-oriented Trajectory Prediction for Interacting Vehicles with Vectorized Representation

Ding Li, Qichao Zhang, Shuai Lu, Yifeng Pan, Dongbin Zhao

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 14 pages, 4 figures

2210.13846 2022-10-26 cs.LG cs.RO 57%

Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning

Yi Zhao, Rinu Boney, Alexander Ilin, Juho Kannala, Joni Pajarinen

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2210.07773 2022-10-26 cs.IR cs.GT cs.LG 57%

Diversified Recommendations for Agents with Adaptive Preferences

Arpit Agarwal, William Brown

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 34 pages, forthcoming in NeurIPS 2022

2210.12942 2022-10-25 cs.CL 57%

Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?

Zhiqiang Hu, Roy Kaa-Wei Lee, Nancy F. Chen

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments 12 pages

2210.12806 2022-10-25 cs.RO cs.LG 57%

Active Exploration for Robotic Manipulation

Tim Schneider, Boris Belousov, Georgia Chalvatzaki, Diego Romeres, Devesh K. Jha, Jan Peters

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Published without appendix at "International Conference on Intelligent Robots and Systems (IROS)" 2022

2210.12509 2022-10-25 cs.CV cs.LG 57%

Cut-and-Approximate: 3D Shape Reconstruction from Planar Cross-sections with Deep Reinforcement Learning

Azimkhon Ostonov

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 13 pages; NeurIPS paper

2210.12448 2022-10-25 cs.LG 57%

Probing Transfer in Deep Reinforcement Learning without Task Engineering

Andrei A. Rusu, Sebastian Flennerhag, Dushyant Rao, Razvan Pascanu, Raia Hadsell

专题命中 Agent评测：agent(abstract)；分类 cs.LG

1604.02509 2022-10-20 cs.AI 57%

Towards an Indexical Model of Situated Language Comprehension for Cognitive Agents in Physical Worlds

Shiwali Mohan, Aaron Mininger, John Laird

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Journal ref Advances in Cognitive Systems 3 (2014)

2210.07851 2022-10-18 cs.RO cs.AI 57%

Learning to Autonomously Reach Objects with NICO and Grow-When-Required Networks

Nima Rahrakhshan, Matthias Kerzel, Philipp Allgeuer, Nicolas Duczek, Stefan Wermter

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments Accepted at the 2022 IEEE-RAS International Conference on Humanoid Robots (Humanoids 2022)

2210.06784 2022-10-17 cs.ET cs.LG quant-ph 57%

Efficient circuit implementation for coined quantum walks on binary trees and application to reinforcement learning

Thomas Mullor, David Vigouroux, Louis Bethune

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Journal ref ACM/IEEE International Workshop on Quantum Computing, Dec 2022, Seattle, United States

2202.06690 2022-10-14 cs.CL 57%

ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers

Federico Ruggeri, Mohsen Mesgar, Iryna Gurevych

专题命中 Agent评测：agent(abstract)；分类 cs.CL

2210.04002 2022-10-11 cs.LG 57%

Dynamically meeting performance objectives for multiple services on a service mesh

Forough Shahab Samani, Rolf Stadler

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Accepted at the 18th International Conference on Network and Service Management

2210.03325 2022-10-10 cs.LG 57%

Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks

Adrian Ly, Richard Dazeley, Peter Vamplew, Francisco Cruz, Sunil Aryal

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2210.02552 2022-10-07 cs.LG 57%

Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning

Flemming Kondrup, Thomas Jiralerspong, Elaine Lau, Nathan de Lara, Jacob Shkrob, My Duc Tran, Doina Precup, Sumana Basu

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments to be published in IAAI (Innovative Applications of Artificial Intelligence) 2023

1. Agent评测 15867 篇

A deep learning framework to generate realistic population and mobility data

Generalizing distribution of partial rewards for multi-armed bandits with temporally-partitioned rewards

Evaluation of tools for describing, reproducing and reusing scientific workflows

A data-driven approach for learning to control computers

Job Scheduling in Datacenters using Constraint Controlled RL

Leveraging Fully Observable Policies for Learning under Partial Observability

Formalizing the Problem of Side Effect Regularization

Synthesis of separation processes with reinforcement learning

Stress Propagation in Human-Robot Teams Based on Computational Logic Model

The Curious Case of Control

Coordination with Humans via Strategy Matching

Learning body models: from humans to humanoids

Body models in humans, animals, and robots: mechanisms and plasticity

Approximate exploitability: Learning a best response in large games

A space of goals: the cognitive geometry of informationally bounded agents

SocialVAE: Human Trajectory Prediction using Timewise Latents

Conditional Goal-oriented Trajectory Prediction for Interacting Vehicles with Vectorized Representation

Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning

Diversified Recommendations for Agents with Adaptive Preferences

Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?

Active Exploration for Robotic Manipulation

Cut-and-Approximate: 3D Shape Reconstruction from Planar Cross-sections with Deep Reinforcement Learning

Probing Transfer in Deep Reinforcement Learning without Task Engineering

Towards an Indexical Model of Situated Language Comprehension for Cognitive Agents in Physical Worlds

Learning to Autonomously Reach Objects with NICO and Grow-When-Required Networks

Efficient circuit implementation for coined quantum walks on binary trees and application to reinforcement learning

ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers

Dynamically meeting performance objectives for multiple services on a service mesh

Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks

Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning