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 Dale Schuurmans

On the Sample Complexity of Batch Reinforcement Learning with Policy-Induced Data


Jun 18, 2021
Chenjun Xiao, Ilbin Lee, Bo Dai, Dale Schuurmans, Csaba Szepesvari

* 26 pages, 2 figures 

  Access Paper or Ask Questions

Characterizing the Gap Between Actor-Critic and Policy Gradient


Jun 13, 2021
Junfeng Wen, Saurabh Kumar, Ramki Gummadi, Dale Schuurmans

* ICML 2021 

  Access Paper or Ask Questions

Leveraging Non-uniformity in First-order Non-convex Optimization


May 13, 2021
Jincheng Mei, Yue Gao, Bo Dai, Csaba Szepesvari, Dale Schuurmans

* 48 pages, 10 figures. Accepted at ICML 2021 

  Access Paper or Ask Questions

Joint Attention for Multi-Agent Coordination and Social Learning


Apr 15, 2021
Dennis Lee, Natasha Jaques, Chase Kew, Douglas Eck, Dale Schuurmans, Aleksandra Faust


  Access Paper or Ask Questions

On the Optimality of Batch Policy Optimization Algorithms


Apr 06, 2021
Chenjun Xiao, Yifan Wu, Tor Lattimore, Bo Dai, Jincheng Mei, Lihong Li, Csaba Szepesvari, Dale Schuurmans

* 29 pages, 8 figures 

  Access Paper or Ask Questions

Optimization Issues in KL-Constrained Approximate Policy Iteration


Feb 11, 2021
Nevena Lazić, Botao Hao, Yasin Abbasi-Yadkori, Dale Schuurmans, Csaba Szepesvári


  Access Paper or Ask Questions

Offline Policy Selection under Uncertainty


Dec 12, 2020
Mengjiao Yang, Bo Dai, Ofir Nachum, George Tucker, Dale Schuurmans


  Access Paper or Ask Questions

Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration


Nov 10, 2020
Hanjun Dai, Rishabh Singh, Bo Dai, Charles Sutton, Dale Schuurmans

* NeurIPS 2020 

  Access Paper or Ask Questions

CoinDICE: Off-Policy Confidence Interval Estimation


Oct 22, 2020
Bo Dai, Ofir Nachum, Yinlam Chow, Lihong Li, Csaba Szepesvári, Dale Schuurmans

* To appear at NeurIPS 2020 as spotlight 

  Access Paper or Ask Questions

Attention that does not Explain Away


Sep 29, 2020
Nan Ding, Xinjie Fan, Zhenzhong Lan, Dale Schuurmans, Radu Soricut


  Access Paper or Ask Questions

EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL


Jul 21, 2020
Seyed Kamyar Seyed Ghasemipour, Dale Schuurmans, Shixiang Shane Gu


  Access Paper or Ask Questions

Off-Policy Evaluation via the Regularized Lagrangian


Jul 07, 2020
Mengjiao Yang, Ofir Nachum, Bo Dai, Lihong Li, Dale Schuurmans


  Access Paper or Ask Questions

Go Wide, Then Narrow: Efficient Training of Deep Thin Networks


Jul 01, 2020
Denny Zhou, Mao Ye, Chen Chen, Tianjian Meng, Mingxing Tan, Xiaodan Song, Quoc Le, Qiang Liu, Dale Schuurmans

* ICML 2020 

  Access Paper or Ask Questions

Scalable Deep Generative Modeling for Sparse Graphs


Jun 28, 2020
Hanjun Dai, Azade Nazi, Yujia Li, Bo Dai, Dale Schuurmans

* ICML 2020 

  Access Paper or Ask Questions

A maximum-entropy approach to off-policy evaluation in average-reward MDPs


Jun 17, 2020
Nevena Lazic, Dong Yin, Mehrdad Farajtabar, Nir Levine, Dilan Gorur, Chris Harris, Dale Schuurmans


  Access Paper or Ask Questions

On the Global Convergence Rates of Softmax Policy Gradient Methods


May 13, 2020
Jincheng Mei, Chenjun Xiao, Csaba Szepesvari, Dale Schuurmans

* 57 pages 

  Access Paper or Ask Questions

Energy-Based Processes for Exchangeable Data


Mar 17, 2020
Mengjiao Yang, Bo Dai, Hanjun Dai, Dale Schuurmans


  Access Paper or Ask Questions

Variational Inference for Deep Probabilistic Canonical Correlation Analysis


Mar 09, 2020
Mahdi Karami, Dale Schuurmans

* 13 pages, 4 figures 

  Access Paper or Ask Questions

Batch Stationary Distribution Estimation


Mar 02, 2020
Junfeng Wen, Bo Dai, Lihong Li, Dale Schuurmans


  Access Paper or Ask Questions

ConQUR: Mitigating Delusional Bias in Deep Q-learning


Feb 27, 2020
Andy Su, Jayden Ooi, Tyler Lu, Dale Schuurmans, Craig Boutilier


  Access Paper or Ask Questions

GenDICE: Generalized Offline Estimation of Stationary Values


Feb 21, 2020
Ruiyi Zhang, Bo Dai, Lihong Li, Dale Schuurmans

* ICLR 2020 

  Access Paper or Ask Questions

Learning to Combat Compounding-Error in Model-Based Reinforcement Learning


Dec 24, 2019
Chenjun Xiao, Yifan Wu, Chen Ma, Dale Schuurmans, Martin Müller


  Access Paper or Ask Questions

AlgaeDICE: Policy Gradient from Arbitrary Experience


Dec 04, 2019
Ofir Nachum, Bo Dai, Ilya Kostrikov, Yinlam Chow, Lihong Li, Dale Schuurmans


  Access Paper or Ask Questions

Domain Aggregation Networks for Multi-Source Domain Adaptation


Sep 25, 2019
Junfeng Wen, Russell Greiner, Dale Schuurmans


  Access Paper or Ask Questions

Striving for Simplicity in Off-policy Deep Reinforcement Learning


Jul 10, 2019
Rishabh Agarwal, Dale Schuurmans, Mohammad Norouzi


  Access Paper or Ask Questions

Advantage Amplification in Slowly Evolving Latent-State Environments


May 29, 2019
Martin Mladenov, Ofer Meshi, Jayden Ooi, Dale Schuurmans, Craig Boutilier


  Access Paper or Ask Questions

Exponential Family Estimation via Adversarial Dynamics Embedding


Apr 27, 2019
Bo Dai, Zhen Liu, Hanjun Dai, Niao He, Arthur Gretton, Le Song, Dale Schuurmans

* 66 figures, 25 pages; preliminary version published in NeurIPS2018 Bayesian Deep Learning Workshop 

  Access Paper or Ask Questions

Learning to Generalize from Sparse and Underspecified Rewards


Feb 19, 2019
Rishabh Agarwal, Chen Liang, Dale Schuurmans, Mohammad Norouzi


  Access Paper or Ask Questions

The Value Function Polytope in Reinforcement Learning


Feb 15, 2019
Robert Dadashi, Adrien Ali Taïga, Nicolas Le Roux, Dale Schuurmans, Marc G. Bellemare


  Access Paper or Ask Questions