Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Paul Weng

Generalization in Deep RL for TSP Problems via Equivariance and Local Search


Oct 07, 2021
Wenbin Ouyang, Yisen Wang, Paul Weng, Shaochen Han

* 18 pages, 2 figures 

  Access Paper or Ask Questions

Improving Generalization of Deep Reinforcement Learning-based TSP Solvers


Oct 06, 2021
Wenbin Ouyang, Yisen Wang, Shaochen Han, Zhejian Jin, Paul Weng

* 8 pages, 2 figures 

  Access Paper or Ask Questions

Learning Symbolic Rules for Interpretable Deep Reinforcement Learning


Mar 16, 2021
Zhihao Ma, Yuzheng Zhuang, Paul Weng, Hankz Hankui Zhuo, Dong Li, Wulong Liu, Jianye Hao


  Access Paper or Ask Questions

Safe Distributional Reinforcement Learning


Feb 26, 2021
Jianyi Zhang, Paul Weng


  Access Paper or Ask Questions

Differentiable Logic Machines


Feb 24, 2021
Matthieu Zimmer, Xuening Feng, Claire Glanois, Zhaohui Jiang, Jianyi Zhang, Paul Weng, Hao Jianye, Li Dong, Liu Wulong


  Access Paper or Ask Questions

Analytics and Machine Learning in Vehicle Routing Research


Feb 19, 2021
Ruibin Bai, Xinan Chen, Zhi-Long Chen, Tianxiang Cui, Shuhui Gong, Wentao He, Xiaoping Jiang, Huan Jin, Jiahuan Jin, Graham Kendall, Jiawei Li, Zheng Lu, Jianfeng Ren, Paul Weng, Ning Xue, Huayan Zhang

* Submitted to International Journal of Production Research 

  Access Paper or Ask Questions

Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning


Dec 17, 2020
Matthieu Zimmer, Umer Siddique, Paul Weng


  Access Paper or Ask Questions

Hyperparameter Auto-tuning in Self-Supervised Robotic Learning


Oct 19, 2020
Jiancong Huang, Juan Rojas, Matthieu Zimmer, Hongmin Wu, Yisheng Guan, Paul Weng


  Access Paper or Ask Questions

Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewards


Aug 18, 2020
Umer Siddique, Paul Weng, Matthieu Zimmer


  Access Paper or Ask Questions

Reinforcement Learning


Jun 13, 2020
Olivier Buffet, Olivier Pietquin, Paul Weng

* Chapter in "A Guided Tour of Artificial Intelligence Research", Springer 

  Access Paper or Ask Questions

Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation


Nov 15, 2019
Yijiong Lin, Jiancong Huang, Matthieu Zimmer, Juan Rojas, Paul Weng

* NeurIPS 2019 Workshop on Robot Learning: Control and Interaction in the Real World (accepted after double-blind peer review). arXiv admin note: substantial text overlap with arXiv:1909.10707 

  Access Paper or Ask Questions

Invariant Transform Experience Replay


Oct 10, 2019
Yijiong Lin, Jiancong Huang, Matthieu Zimmer, Juan Rojas, Paul Weng

* 7 pages, 6 figures 

  Access Paper or Ask Questions

Fairness in Reinforcement Learning


Jul 24, 2019
Paul Weng

* Presented at the AI for Social Good Workshop at IJCAI 2019 

  Access Paper or Ask Questions

Exploiting the Sign of the Advantage Function to Learn Deterministic Policies in Continuous Domains


Jun 25, 2019
Matthieu Zimmer, Paul Weng

* International Joint Conferences on Artificial Intelligence 

  Access Paper or Ask Questions

Exploiting the sign of the advantage function to learn deterministic policies in continuous domains


Jun 10, 2019
Matthieu Zimmer, Paul Weng

* International Joint Conferences on Artificial Intelligence 

  Access Paper or Ask Questions

Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems


Mar 25, 2019
Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Peng He, Paul Weng, Han Gao, Guihai Chen

* Accepted by WWW2019 as a full paper with oral presentation 

  Access Paper or Ask Questions

Multi-objective Bandits: Optimizing the Generalized Gini Index


Jun 15, 2017
Robert Busa-Fekete, Balazs Szorenyi, Paul Weng, Shie Mannor

* 13 pages, 3 figures, draft version of ICML'17 paper 

  Access Paper or Ask Questions

From Preference-Based to Multiobjective Sequential Decision-Making


Jan 03, 2017
Paul Weng

* accepted at MIWAI 2017 

  Access Paper or Ask Questions

Finding Risk-Averse Shortest Path with Time-dependent Stochastic Costs


Jan 03, 2017
Dajian Li, Paul Weng, Orkun Karabasoglu

* accepted at MIWAI 2017 

  Access Paper or Ask Questions

Optimizing Quantiles in Preference-based Markov Decision Processes


Dec 01, 2016
Hugo Gilbert, Paul Weng, Yan Xu

* Long version of AAAI 2017 paper. arXiv admin note: text overlap with arXiv:1611.00862 

  Access Paper or Ask Questions

Quantile Reinforcement Learning


Nov 03, 2016
Hugo Gilbert, Paul Weng

* AWRL 2016 

  Access Paper or Ask Questions

Approximation of Lorenz-Optimal Solutions in Multiobjective Markov Decision Processes


Sep 26, 2013
Patrice Perny, Paul Weng, Judy Goldsmith, Josiah Hanna

* Appears in Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI2013) 

  Access Paper or Ask Questions

Qualitative Decision Making Under Possibilistic Uncertainty: Toward more discriminating criteria


Jul 04, 2012
Paul Weng

* Appears in Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI2005) 

  Access Paper or Ask Questions

Axiomatic Foundations for a Class of Generalized Expected Utility: Algebraic Expected Utility


Jun 27, 2012
Paul Weng

* Appears in Proceedings of the Twenty-Second Conference on Uncertainty in Artificial Intelligence (UAI2006) 

  Access Paper or Ask Questions