AI Agent - arXivDaily 专题

2207.03635 2022-07-11 cs.LG 57%

Information-Gathering in Latent Bandits

Alexander Galozy, Slawomir Nowaczyk

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2202.03060 2022-07-11 cs.LG 57%

The Importance of Non-Markovianity in Maximum State Entropy Exploration

Mirco Mutti, Riccardo De Santi, Marcello Restelli

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments ICML 2022

2206.15352 2022-07-01 cs.LG cs.NE 57%

Learning Citywide Patterns of Life from Trajectory Monitoring

Mark Tenzer, Zeeshan Rasheed, Khurram Shafique

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

Comments 12 pages, 9 figures (including 2 pages and 2 figures in Appendix). Submitted to SIGSPATIAL 2022

2104.04342 2022-06-29 cs.RO cs.LG 57%

Distributed Bayesian Online Learning for Cooperative Manipulation

Pablo Budde gen. Dohmann, Armin Lederer, Marcel Dißemond, Sandra Hirche

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2206.12441 2022-06-28 cs.LG 57%

Joint Representation Training in Sequential Tasks with Shared Structure

Aldo Pacchiano, Ofir Nachum, Nilseh Tripuraneni, Peter Bartlett

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2205.12184 2022-06-20 cs.LG math.OC stat.ML 57%

Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning

Harley Wiltzer, David Meger, Marc G. Bellemare

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

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

2106.07995 2022-06-07 cs.LG cs.CV cs.RO 57%

Learning of feature points without additional supervision improves reinforcement learning from images

Rinu Boney, Alexander Ilin, Juho Kannala

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2205.00436 2022-06-06 cs.LG cs.CR 57%

Differentially Private Multivariate Time Series Forecasting of Aggregated Human Mobility With Deep Learning: Input or Gradient Perturbation?

Héber H. Arcolezi, Jean-François Couchot, Denis Renaud, Bechara Al Bouna, Xiaokui Xiao

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

Comments Final version accepted in the journal Neural Computing and Applications

2205.13834 2022-05-30 cs.LG 57%

Improving Bidding and Playing Strategies in the Trick-Taking game Wizard using Deep Q-Networks

Jonas Schumacher, Marco Pleines

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted to IEEE CoG 2022, 8 pages, 17 figures

2204.02041 2022-05-27 cs.LG cs.RO 57%

Automating Reinforcement Learning with Example-based Resets

Jigang Kim, J. hyeon Park, Daesol Cho, H. Jin Kim

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 8 pages, 6 figures; accepted for publication in the IEEE Robotics and Automation Letters (RA-L); source code available at https://github.com/jigangkim/autoreset_rl ; supplementary video available at https://youtu.be/himd0Z5b64A

Journal ref IEEE Robotics and Automation Letters 7 (2022) 6606-6613

2205.11507 2022-05-24 cs.LG math.OC stat.ML 57%

Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs

Dongruo Zhou, Quanquan Gu

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

Comments 33 pages, 1 table

2205.10729 2022-05-24 cs.LG 57%

Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path

Haoyuan Cai, Tengyu Ma, Simon Du

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments ICML 2022

2205.10407 2022-05-24 cs.LG 57%

Prototyping three key properties of specific curiosity in computational reinforcement learning

Nadia M. Ady, Roshan Shariff, Johannes Günther, Patrick M. Pilarski

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 5 pages, 6 figures, accepted at the 5th Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM2022), June 8-11, 2022

2205.09448 2022-05-20 cs.AI cs.CV 57%

Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes

Zheng Fang, Biao Zhao, Guizhong Liu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2204.13060 2022-05-18 cs.LG 57%

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning

Philippe Hansen-Estruch, Amy Zhang, Ashvin Nair, Patrick Yin, Sergey Levine

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments ICML 2022. 20 Pages, 15 Figures, 4 Tables. Website at https://sites.google.com/view/gc-bisimulation

2110.05128 2022-05-12 cs.LG 57%

REIN-2: Giving Birth to Prepared Reinforcement Learning Agents Using Reinforcement Learning Agents

Aristotelis Lazaridis, Ioannis Vlahavas

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Journal ref Neurocomputing 497 (2022) 86-93

2205.01435 2022-05-11 cs.LG 57%

RLFlow: Optimising Neural Network Subgraph Transformation with World Models

Sean Parker, Sami Alabed, Eiko Yoneki

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 14 pages, 11 figures

2108.01176 2022-05-09 cs.RO cs.AI 57%

Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks

Zachary Ravichandran, Lisa Peng, Nathan Hughes, J. Daniel Griffith, Luca Carlone

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Accepted by the International Conference on Robotics and Automation (ICRA) 2022

2205.01965 2022-05-05 cs.LG 57%

State Representation Learning for Goal-Conditioned Reinforcement Learning

Lorenzo Steccanella, Anders Jonsson

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

2205.00399 2022-05-03 cs.AI 57%

Learning user-defined sub-goals using memory editing in reinforcement learning

GyeongTaek Lee

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2204.10849 2022-04-25 cs.CL 57%

Metric Learning and Adaptive Boundary for Out-of-Domain Detection

Petr Lorenc, Tommaso Gargiani, Jan Pichl, Jakub Konrád, Petr Marek, Ondřej Kobza, Jan Šedivý

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments Accepted to The 27th International Conference on Natural Language & Information Systems (NLDB) 2022

2203.02956 2022-04-21 cs.AI q-bio.NC 57%

What does it mean to represent? Mental representations as falsifiable memory patterns

Eloy Parra-Barrero, Yulia Sandamirskaya

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

2204.05173 2022-04-15 cs.LG cs.CV 57%

Machine Learning State-of-the-Art with Uncertainties

Peter Steinbach, Felicita Gernhardt, Mahnoor Tanveer, Steve Schmerler, Sebastian Starke

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

Comments 9 pages, 6 figures. Accepted at the ICLR2022 workshop on ML Evaluation Standards. Code to reproduce results can be obtained from https://github.com/psteinb/sota_on_uncertainties.git

2204.05509 2022-04-13 cs.RO cs.AI 57%

Learning Design and Construction with Varying-Sized Materials via Prioritized Memory Resets

Yunfei Li, Tao Kong, Lei Li, Yi Wu

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

Comments To be published in ICRA 2022

2203.04172 2022-04-07 cs.AI cs.SY eess.SY 57%

Distributed Control using Reinforcement Learning with Temporal-Logic-Based Reward Shaping

Ningyuan Zhang, Wenliang Liu, Calin Belta

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 12 pages, 4 figures, accepted by L4DC 2022

2204.01975 2022-04-06 cs.CR cs.LG 57%

GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning

Jinyin Chen, Shulong Hu, Haibin Zheng, Changyou Xing, Guomin Zhang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2203.11024 2022-03-22 cs.AI cs.RO cs.SY eess.SY 57%

Multi-View Dreaming: Multi-View World Model with Contrastive Learning

Akira Kinose, Masashi Okada, Ryo Okumura, Tadahiro Taniguchi

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 7 pages, 8 figures

2007.02929 2022-03-22 cs.LG stat.ML 57%

IMU Preintegrated Features for Efficient Deep Inertial Odometry

R. Khorrambakht, H. Damirchi, H. D. Taghirad

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2203.03875 2022-03-09 cs.RO cs.LG 57%

Occupancy Flow Fields for Motion Forecasting in Autonomous Driving

Reza Mahjourian, Jinkyu Kim, Yuning Chai, Mingxing Tan, Ben Sapp, Dragomir Anguelov

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Journal ref IEEE Robotics and Automation Letters

2104.14332 2022-03-09 cs.LG cs.SY eess.SY 57%

Hypernetwork Dismantling via Deep Reinforcement Learning

Dengcheng Yan, Wenxin Xie, Yiwen Zhang, Qiang He, Yun Yang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1. 记忆与上下文管理 4758 篇

Information-Gathering in Latent Bandits

The Importance of Non-Markovianity in Maximum State Entropy Exploration

Learning Citywide Patterns of Life from Trajectory Monitoring

Distributed Bayesian Online Learning for Cooperative Manipulation

Joint Representation Training in Sequential Tasks with Shared Structure

Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning

Learning of feature points without additional supervision improves reinforcement learning from images

Differentially Private Multivariate Time Series Forecasting of Aggregated Human Mobility With Deep Learning: Input or Gradient Perturbation?

Improving Bidding and Playing Strategies in the Trick-Taking game Wizard using Deep Q-Networks

Automating Reinforcement Learning with Example-based Resets

Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs

Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path

Prototyping three key properties of specific curiosity in computational reinforcement learning

Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning

REIN-2: Giving Birth to Prepared Reinforcement Learning Agents Using Reinforcement Learning Agents

RLFlow: Optimising Neural Network Subgraph Transformation with World Models

Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks

State Representation Learning for Goal-Conditioned Reinforcement Learning

Learning user-defined sub-goals using memory editing in reinforcement learning

Metric Learning and Adaptive Boundary for Out-of-Domain Detection

What does it mean to represent? Mental representations as falsifiable memory patterns

Machine Learning State-of-the-Art with Uncertainties

Learning Design and Construction with Varying-Sized Materials via Prioritized Memory Resets

Distributed Control using Reinforcement Learning with Temporal-Logic-Based Reward Shaping

GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning

Multi-View Dreaming: Multi-View World Model with Contrastive Learning

IMU Preintegrated Features for Efficient Deep Inertial Odometry

Occupancy Flow Fields for Motion Forecasting in Autonomous Driving

Hypernetwork Dismantling via Deep Reinforcement Learning