AI Agent - arXivDaily 专题

1907.08313 2019-07-22 cs.AI cs.LG 81%

Learning High-Level Planning Symbols from Intrinsically Motivated Experience

Angelo Oddi, Riccardo Rasconi, Emilio Cartoni, Gabriele Sartor, Gianluca Baldassarre, Vieri Giuliano Santucci

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

1907.04799 2019-07-15 cs.RO cs.AI cs.LG 81%

RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators from RL Policies

Hao-Tien Lewis Chiang, Jasmine Hsu, Marek Fiser, Lydia Tapia, Aleksandra Faust

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

Comments Accepted to Robotics and Automation Letters in June 2019

Journal ref Robotics and Automation Letters 2019

1907.04457 2019-07-11 cs.RO cs.AI cs.LG 81%

Partially Observable Planning and Learning for Systems with Non-Uniform Dynamics

Nicholas Collins, Hanna Kurniawati

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

1906.08649 2019-06-21 cs.LG cs.AI cs.RO stat.ML 81%

Exploring Model-based Planning with Policy Networks

Tingwu Wang, Jimmy Ba

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

Comments 8 pages, 7 figures

1904.03396 2019-05-03 cs.CL cs.AI 81%

Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation

Amit Moryossef, Yoav Goldberg, Ido Dagan

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

Comments 9 main pages, 10 appendix pages

1904.11102 2019-04-26 cs.RO cs.AI cs.LG 81%

Neural Path Planning: Fixed Time, Near-Optimal Path Generation via Oracle Imitation

Mayur J. Bency, Ahmed H. Qureshi, Michael C. Yip

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

1810.09923 2019-04-12 cs.AI cs.LG 81%

Learning Classical Planning Strategies with Policy Gradient

Pawel Gomoluch, Dalal Alrajeh, Alessandra Russo

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

Comments Accepted for ICAPS 2019

1903.03234 2019-03-11 cs.LG cs.AI stat.ML 81%

Dyna-AIL : Adversarial Imitation Learning by Planning

Vaibhav Saxena, Srinivasan Sivanandan, Pulkit Mathur

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

Comments 8 pages, 6 figures, pre-print

1812.01127 2019-02-04 cs.RO cs.AI cs.LG 81%

Learning to Predict Ego-Vehicle Poses for Sampling-Based Nonholonomic Motion Planning

Holger Banzhaf, Paul Sanzenbacher, Ulrich Baumann, J. Marius Zöllner

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

Comments Extended version of DOI 10.1109/LRA.2019.2893975, IEEE Robotics and Automation Letters, 2019

1901.06569 2019-01-23 cs.LG cs.AI stat.ML 81%

Learning retrosynthetic planning through self-play

John S. Schreck, Connor W. Coley, Kyle J. M. Bishop

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

1609.07560 2019-01-10 cs.RO cs.AI cs.LG stat.ML 81%

Informative Planning and Online Learning with Sparse Gaussian Processes

Kai-Chieh Ma, Lantao Liu, Gaurav S. Sukhatme

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

1812.10972 2019-01-08 cs.LG cs.AI cs.CV cs.RO stat.ML 81%

Reasoning About Physical Interactions with Object-Oriented Prediction and Planning

Michael Janner, Sergey Levine, William T. Freeman, Joshua B. Tenenbaum, Chelsea Finn, Jiajun Wu

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

Comments ICLR 2019, project page: https://people.eecs.berkeley.edu/~janner/o2p2/

1901.01325 2019-01-08 cs.LG cs.AI 81%

Optimal Decision-Making in Mixed-Agent Partially Observable Stochastic Environments via Reinforcement Learning

Roi Ceren

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

Comments Phd thesis, University of Georgia (2018)

1811.12454 2018-12-03 cs.SE cs.AI 81%

A rule-based system proposal to aid in the evaluation and decision-making in external beam radiation treatment planning

R. C. Fernandes, T. M. Machado, H. J. Onisto, A. D. Muñoz, R. O. Silva, L. R. Domingues, G. C. Fonseca, J. E. Bertuzzo, M. T. Pereira, B. Biazotto, E. T. Costa

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

Comments 20 pages

1811.10097 2018-11-27 cs.LG cs.AI cs.RO stat.ML 81%

Planning in Dynamic Environments with Conditional Autoregressive Models

Johanna Hansen, Kyle Kastner, Aaron Courville, Gregory Dudek

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

Comments 6 pages, 1 figure, in Proceedings of the Prediction and Generative Modeling in Reinforcement Learning Workshop at the International Conference on Machine Learning (ICML) in 2018

1811.08955 2018-11-26 cs.RO cs.AI cs.LG 81%

Integrating Task-Motion Planning with Reinforcement Learning for Robust Decision Making in Mobile Robots

Yuqian Jiang, Fangkai Yang, Shiqi Zhang, Peter Stone

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

1811.04350 2018-11-13 cs.LG cs.AI stat.ML 81%

Towards Governing Agent's Efficacy: Action-Conditional $β$-VAE for Deep Transparent Reinforcement Learning

John Yang, Gyujeong Lee, Minsung Hyun, Simyung Chang, Nojun Kwak

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

1808.10120 2018-10-26 cs.AI cs.GT cs.LG 81%

ExIt-OOS: Towards Learning from Planning in Imperfect Information Games

Andy Kitchen, Michela Benedetti

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

Comments 8 pages. 1 figure, 5 tables

1810.00482 2018-10-02 cs.LG cs.AI cs.CV cs.RO stat.ML 81%

Few-Shot Goal Inference for Visuomotor Learning and Planning

Annie Xie, Avi Singh, Sergey Levine, Chelsea Finn

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

Comments Videos available at https://sites.google.com/view/few-shot-goals

1809.02855 2018-09-11 cs.CY cs.AI cs.LG eess.SP stat.ML 81%

iDriveSense: Dynamic Route Planning Involving Roads Quality Information

Amr S. El-Wakeel, Aboelmagd Noureldin, Hossam S. Hassanein, Nizar Zorba

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

Comments Globecom 2018

1803.00967 2018-08-14 cs.RO cs.AI cs.LG stat.AP stat.ML 81%

Active model learning and diverse action sampling for task and motion planning

Zi Wang, Caelan Reed Garrett, Leslie Pack Kaelbling, Tomás Lozano-Pérez

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

Comments Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain. https://www.youtube.com/playlist?list=PLoWhBFPMfSzDbc8CYelsbHZa1d3uz-W_c

1607.07762 2018-08-06 cs.AI cs.LG cs.RO stat.AP stat.ML 81%

Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems

Zi Wang, Stefanie Jegelka, Leslie Pack Kaelbling, Tomás Lozano-Pérez

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

1807.09962 2018-07-27 cs.RO cs.AI cs.LG 81%

Learning to guide task and motion planning using score-space representation

Beomjoon Kim, Zi Wang, Leslie Pack Kaelbling, Tomas Lozano-Perez

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

1807.06696 2018-07-19 cs.RO cs.AI cs.LG 81%

Integrating Algorithmic Planning and Deep Learning for Partially Observable Navigation

Peter Karkus, David Hsu, Wee Sun Lee

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

Comments MLPC workshop, ICRA 2018

1806.06408 2018-06-19 cs.LG cs.AI cs.RO stat.ML 81%

Gated Path Planning Networks

Lisa Lee, Emilio Parisotto, Devendra Singh Chaplot, Eric Xing, Ruslan Salakhutdinov

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

Comments ICML 2018

1804.00645 2018-04-05 cs.LG cs.AI cs.CV cs.RO stat.ML 81%

Universal Planning Networks

Aravind Srinivas, Allan Jabri, Pieter Abbeel, Sergey Levine, Chelsea Finn

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

Comments Videos available at https://sites.google.com/view/upn-public/home

1703.06692 2017-11-06 cs.AI cs.LG cs.NE stat.ML 81%

QMDP-Net: Deep Learning for Planning under Partial Observability

Peter Karkus, David Hsu, Wee Sun Lee

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

Comments NIPS 2017 camera-ready

1710.05268 2017-10-18 cs.RO cs.AI cs.CV cs.LG 81%

Self-Supervised Visual Planning with Temporal Skip Connections

Frederik Ebert, Chelsea Finn, Alex X. Lee, Sergey Levine

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

Comments accepted at the Conference on Robot Learning (CoRL) 2017

1612.08810 2017-07-21 cs.LG cs.AI cs.NE 81%

The Predictron: End-To-End Learning and Planning

David Silver, Hado van Hasselt, Matteo Hessel, Tom Schaul, Arthur Guez, Tim Harley, Gabriel Dulac-Arnold, David Reichert, Neil Rabinowitz, Andre Barreto, Thomas Degris

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

Comments Camera-ready version, ICML 2017, with supplement

1610.00696 2017-03-14 cs.LG cs.AI cs.CV cs.RO 81%

Deep Visual Foresight for Planning Robot Motion

Chelsea Finn, Sergey Levine

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

Comments ICRA 2017. Supplementary video: https://sites.google.com/site/robotforesight/

1. 规划决策 35504 篇

Learning High-Level Planning Symbols from Intrinsically Motivated Experience

RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators from RL Policies

Partially Observable Planning and Learning for Systems with Non-Uniform Dynamics

Exploring Model-based Planning with Policy Networks

Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation

Neural Path Planning: Fixed Time, Near-Optimal Path Generation via Oracle Imitation

Learning Classical Planning Strategies with Policy Gradient

Dyna-AIL : Adversarial Imitation Learning by Planning

Learning to Predict Ego-Vehicle Poses for Sampling-Based Nonholonomic Motion Planning

Learning retrosynthetic planning through self-play

Informative Planning and Online Learning with Sparse Gaussian Processes

Reasoning About Physical Interactions with Object-Oriented Prediction and Planning

Optimal Decision-Making in Mixed-Agent Partially Observable Stochastic Environments via Reinforcement Learning

A rule-based system proposal to aid in the evaluation and decision-making in external beam radiation treatment planning

Planning in Dynamic Environments with Conditional Autoregressive Models

Integrating Task-Motion Planning with Reinforcement Learning for Robust Decision Making in Mobile Robots

Towards Governing Agent's Efficacy: Action-Conditional $β$-VAE for Deep Transparent Reinforcement Learning

ExIt-OOS: Towards Learning from Planning in Imperfect Information Games

Few-Shot Goal Inference for Visuomotor Learning and Planning

iDriveSense: Dynamic Route Planning Involving Roads Quality Information

Active model learning and diverse action sampling for task and motion planning

Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems

Learning to guide task and motion planning using score-space representation

Integrating Algorithmic Planning and Deep Learning for Partially Observable Navigation

Gated Path Planning Networks

Universal Planning Networks

QMDP-Net: Deep Learning for Planning under Partial Observability

Self-Supervised Visual Planning with Temporal Skip Connections

The Predictron: End-To-End Learning and Planning

Deep Visual Foresight for Planning Robot Motion