AI Agent - arXivDaily 专题

2212.04581 2022-12-12 cs.RO cs.AI cs.CV cs.LG 81%

PALMER: Perception-Action Loop with Memory for Long-Horizon Planning

Onur Beker, Mohammad Mohammadi, Amir Zamir

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments Website: https://palmer.epfl.ch

2210.00068 2022-12-09 cs.LG cs.AI cs.RO 81%

Multi-Task Option Learning and Discovery for Stochastic Path Planning

Naman Shah, Siddharth Srivastava

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

2112.09456 2022-12-06 cs.AI cs.LG cs.RO cs.SY eess.SY 81%

Compositional Learning-based Planning for Vision POMDPs

Sampada Deglurkar, Michael H. Lim, Johnathan Tucker, Zachary N. Sunberg, Aleksandra Faust, Claire J. Tomlin

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

2211.15666 2022-11-30 cs.LG cs.AI cs.CV 81%

Learning Visual Planning Models from Partially Observed Images

Kebing Jin, Zhanhao Xiao, Hankui Hankz Zhuo, Hai Wan, Jiaran Cai

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments 25 pages, 5 figures

2210.04971 2022-11-18 cs.LG cs.AI 81%

Multi-step Planning for Automated Hyperparameter Optimization with OptFormer

Lucio M. Dery, Abram L. Friesen, Nando De Freitas, Marc'Aurelio Ranzato, Yutian Chen

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments 8 pages, 7 figures

2211.08368 2022-11-16 cs.RO cs.AI cs.LG 81%

A Survey on the Integration of Machine Learning with Sampling-based Motion Planning

Troy McMahon, Aravind Sivaramakrishnan, Edgar Granados, Kostas E. Bekris

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments First two authors contributed equally

Journal ref Foundations and Trends in Robotics: Vol. 9: No. 4, pp 266-327 (2022)

2210.15755 2022-10-31 cs.LG cs.AI stat.ML 81%

Confident Approximate Policy Iteration for Efficient Local Planning in $q^π$-realizable MDPs

Gellért Weisz, András György, Tadashi Kozuno, Csaba Szepesvári

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

2210.14222 2022-10-26 cs.RO cs.AI cs.CV cs.LG 81%

PlanT: Explainable Planning Transformers via Object-Level Representations

Katrin Renz, Kashyap Chitta, Otniel-Bogdan Mercea, A. Sophia Koepke, Zeynep Akata, Andreas Geiger

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments CoRL 2022. Project Page: https://www.katrinrenz.de/plant/

2210.10602 2022-10-20 cs.CL cs.AI 81%

NGEP: A Graph-based Event Planning Framework for Story Generation

Chen Tang, Zhihao Zhang, Tyler Loakman, Chenghua Lin, Frank Guerin

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.CL

Journal ref AACL 2022

2210.09598 2022-10-19 cs.LG cs.AI 81%

Planning for Sample Efficient Imitation Learning

Zhao-Heng Yin, Weirui Ye, Qifeng Chen, Yang Gao

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2022

2210.08003 2022-10-18 cs.AI cs.LG cs.RO 81%

Hierarchical Decentralized Deep Reinforcement Learning Architecture for a Simulated Four-Legged Agent

W. Zai El Amri, L. Hermes, M. Schilling

专题命中规划决策：agent(title,abstract)；分类 cs.AI、cs.LG

Comments Conference paper (LOD 2022), 15 pages, 8 figures, 4 tables

2210.05236 2022-10-18 cs.AI cs.LG 81%

Planning Assembly Sequence with Graph Transformer

Lin Ma, Jiangtao Gong, Hao Xu, Hao Chen, Hao Zhao, Wenbing Huang, Guyue Zhou

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments Submitted to ICRA2023

2007.16162 2022-10-14 cs.RO cs.AI cs.LG 81%

Imitative Planning using Conditional Normalizing Flow

Shubhankar Agarwal, Harshit Sikchi, Cole Gulino, Eric Wilkinson, Shivam Gautam

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

2206.10680 2022-10-14 cs.RO cs.AI cs.LG 81%

Learning Neuro-Symbolic Skills for Bilevel Planning

Tom Silver, Ashay Athalye, Joshua B. Tenenbaum, Tomas Lozano-Perez, Leslie Pack Kaelbling

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments CoRL 2022

2210.00113 2022-10-04 cs.CL cs.AI cs.IR 81%

Institutional Foundations of Adaptive Planning: Exploration of Flood Planning in the Lower Rio Grande Valley, Texas, USA

Ashley D. Ross, Ali Nejat, Virgie Greb

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.CL

2205.12515 2022-10-03 cs.LG cs.AI 81%

Toward Discovering Options that Achieve Faster Planning

Yi Wan, Richard S. Sutton

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

2208.11079 2022-08-25 cs.RO cs.AI cs.CV cs.LG 81%

Robot Active Neural Sensing and Planning in Unknown Cluttered Environments

Hanwen Ren, Ahmed H. Qureshi

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments https://sites.google.com/view/active-neural-sensing/home

2206.06553 2022-08-25 cs.RO cs.AI cs.CV cs.LG cs.SY eess.SY 81%

Safe Output Feedback Motion Planning from Images via Learned Perception Modules and Contraction Theory

Glen Chou, Necmiye Ozay, Dmitry Berenson

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments Workshop on the Algorithmic Foundations of Robotics (WAFR) XV, 2022, College Park, MD, USA

2208.09966 2022-08-23 cs.LG cs.AI cs.CY 81%

Performance, Opaqueness, Consequences, and Assumptions: Simple questions for responsible planning of machine learning solutions

Przemyslaw Biecek

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

2207.05006 2022-07-12 cs.RO cs.AI cs.LG 81%

TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs

Christopher Agia, Krishna Murthy Jatavallabhula, Mohamed Khodeir, Ondrej Miksik, Vibhav Vineet, Mustafa Mukadam, Liam Paull, Florian Shkurti

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments Video: https://www.youtube.com/watch?v=mM4v5hP4LdA&ab_channel=KrishnaMurthy . Project page: https://taskography.github.io/ . 18 pages, 7 figures. In proceedings of Conference on Robot Learning (CoRL) 2021. The first two authors contributed equally

Journal ref PMLR 164 (2022) 46-58

2105.14074 2022-07-04 cs.AI cs.LG cs.RO 81%

Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning

Rohan Chitnis, Tom Silver, Joshua B. Tenenbaum, Tomas Lozano-Perez, Leslie Pack Kaelbling

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments IROS 2022 final version

2206.11477 2022-06-24 cs.AI cs.LG 81%

RetroGraph: Retrosynthetic Planning with Graph Search

Shufang Xie, Rui Yan, Peng Han, Yingce Xia, Lijun Wu, Chenjuan Guo, Bin Yang, Tao Qin

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments KDD2022

2107.00110 2022-06-17 cs.AI cs.LG 81%

Classical Planning in Deep Latent Space

Masataro Asai, Hiroshi Kajino, Alex Fukunaga, Christian Muise

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments Accepted in Journal of Artificial Intelligence Research (JAIR)

2004.11667 2022-06-10 cs.RO cs.AI cs.LG stat.ML 81%

PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning

Guillaume Matheron, Nicolas Perrin, Olivier Sigaud

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

2206.04114 2022-06-10 cs.AI cs.LG cs.RO stat.ML 81%

Deep Hierarchical Planning from Pixels

Danijar Hafner, Kuang-Huei Lee, Ian Fischer, Pieter Abbeel

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

Comments Website: https://danijar.com/director

2204.01705 2022-05-27 cs.LG cs.AI math.OC 81%

Learning to Accelerate by the Methods of Step-size Planning

Hengshuai Yao

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

2204.11481 2022-04-26 cs.CL cs.AI 81%

"Think Before You Speak": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs

Shuo Zhang, Junzhou Zhao, Pinghui Wang, Yu Li, Yi Huang, Junlan Feng

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.CL

Comments IJCAI 2022 long oral presentation

2202.00907 2022-04-26 cs.RO cs.AI cs.LG 81%

Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning

Naman Shah, Siddharth Srivastava

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

2204.03597 2022-04-19 cs.LG cs.AI 81%

Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning

Carl Qi, Pieter Abbeel, Aditya Grover

专题命中规划决策：planning(title,abstract)；分类 cs.AI、cs.LG

2204.06509 2022-04-14 cs.LG cs.AI cs.RO 81%

Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planning

Ugo Lecerf, Christelle Yemdji-Tchassi, Pietro Michiardi

专题命中规划决策：planning(title)；agent(abstract)；分类 cs.AI、cs.LG

Comments To appear in Generalizable Policy Learning in the Physical World workshop (ICLR 2022)

1. 规划决策 35547 篇

PALMER: Perception-Action Loop with Memory for Long-Horizon Planning

Multi-Task Option Learning and Discovery for Stochastic Path Planning

Compositional Learning-based Planning for Vision POMDPs

Learning Visual Planning Models from Partially Observed Images

Multi-step Planning for Automated Hyperparameter Optimization with OptFormer

A Survey on the Integration of Machine Learning with Sampling-based Motion Planning

Confident Approximate Policy Iteration for Efficient Local Planning in $q^π$-realizable MDPs

PlanT: Explainable Planning Transformers via Object-Level Representations

NGEP: A Graph-based Event Planning Framework for Story Generation

Planning for Sample Efficient Imitation Learning

Hierarchical Decentralized Deep Reinforcement Learning Architecture for a Simulated Four-Legged Agent

Planning Assembly Sequence with Graph Transformer

Imitative Planning using Conditional Normalizing Flow

Learning Neuro-Symbolic Skills for Bilevel Planning

Institutional Foundations of Adaptive Planning: Exploration of Flood Planning in the Lower Rio Grande Valley, Texas, USA

Toward Discovering Options that Achieve Faster Planning

Robot Active Neural Sensing and Planning in Unknown Cluttered Environments

Safe Output Feedback Motion Planning from Images via Learned Perception Modules and Contraction Theory

Performance, Opaqueness, Consequences, and Assumptions: Simple questions for responsible planning of machine learning solutions

TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs

Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning

RetroGraph: Retrosynthetic Planning with Graph Search

Classical Planning in Deep Latent Space

PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning

Deep Hierarchical Planning from Pixels

Learning to Accelerate by the Methods of Step-size Planning

"Think Before You Speak": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs

Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning

Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning

Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planning