Workshop
The Optimization Foundations of Reinforcement Learning
Bo Dai · Niao He · Nicolas Le Roux · Lihong Li · Dale Schuurmans · Martha White

Sat Dec 14th 08:00 AM -- 06:00 PM @ West Ballroom A
Event URL: https://optrl2019.github.io/ »

Interest in reinforcement learning (RL) has boomed with recent improvements in benchmark tasks that suggest the potential for a revolutionary advance in practical applications. Unfortunately, research in RL remains hampered by limited theoretical understanding, making the field overly reliant on empirical exploration with insufficient principles to guide future development. It is imperative to develop a stronger fundamental understanding of the success of recent RL methods, both to expand the useability of the methods and accelerate future deployment. Recently, fundamental concepts from optimization and control theory have provided a fresh perspective that has led to the development of sound RL algorithms with provable efficiency. The goal of this workshop is to catalyze the growing synergy between RL and optimization research, promoting a rational reconsideration of the foundational principles for reinforcement learning, and bridging the gap between theory and practice.

08:00 AM Opening Remarks <span> <a href="#"></a> </span> Bo Dai, Niao He, Nicolas Le Roux, Lihong Li, Dale Schuurmans, Martha White
08:10 AM Unsupervised State Embedding and Aggregation towards Scalable Reinforcement Learning (Plenary Talk) Mengdi Wang
08:50 AM Adaptive Trust Region Policy Optimization: Convergence and Faster Rates of regularized MDPs (Contributed Talk) Lior Shani, Yonathan Efroni, Shie Mannor
09:10 AM Poster Spotlight 1 (Poster Spotlight) David Brandfonbrener, Joan Bruna, Tom Zahavy, Haim Kaplan, Yishay Mansour, Nikos Karampatziakis, John Langford, Paul Mineiro, Donghwan Lee, Niao He
09:30 AM Poster and Coffee Break 1 (Poster Session)
Aaron Sidford, Aditya Mahajan, Alejandro Ribeiro, Alex Lewandowski, Ali H Sayed, Ambuj Tewari, Angelika Steger, Anima Anandkumar, Asier Mujika, Hilbert J Kappen, Bolei Zhou, Byron Boots, Chelsea Finn, Chen-Yu Wei, Chi Jin, Ching-An Cheng, Christina Yu, Clement Gehring, Craig Boutilier, Dahua Lin, Daniel McNamee, Daniel Russo, David Brandfonbrener, Denny Zhou, Devesh Jha, Diego Romeres, Doina Precup, Dominik Thalmeier, Eduard Gorbunov, Elad Hazan, Elena Smirnova, Elvis Dohmatob, Emma Brunskill, Enrique Munoz de Cote, Ethan Waldie, Florian Meier, Florian Schaefer, Ge Liu, Gergely Neu, Haim Kaplan, Hao Sun, Hengshuai Yao, Jalaj Bhandari, James A Preiss, Jayakumar Subramanian, Jiajin Li, Jieping Ye, Jimmy T Smith, Joan Bas Serrano, Joan Bruna, John Langford, Jonathan Lee, Jose A. Arjona-Medina, Kaiqing Zhang, Karan Singh, Yuping Luo, Zafarali Ahmed, Zaiwei Chen, Zhaoran Wang, zz Li, Zhuoran Yang, Ziping Xu, Ziyang Tang, Yi Mao, David Brandfonbrener, Shirli Di-Castro Shashua, Riashat Islam, Zuyue Fu, Abhishek Naik, Saurabh Kumar, Benjamin Petit, Angeliki Kamoutsi, d3sm0 Totaro, Arvind Raghunathan, Rui Wu, Donghwan Lee, Dongsheng Ding, Alec Koppel, Hao Sun, Christian Tjandraatmadja, Mahdi Karami, Jincheng Mei, Chenjun Xiao, Junfeng Wen, Vincent Zhang, Ross Goroshin, Mohammad Pezeshki, Jiaqi Zhai, Philip Amortila, Shuo Huang, Mariya Vasileva, El houcine Bergou, Adel Ahmadyan, Haoran Sun, Sheng Zhang, Lukas Gruber, Yuanhao Wang, Tetiana Parshakova
10:30 AM The Provable Effectiveness of Policy Gradient Methods in Reinforcement Learning (Plenary Talk) Sham Kakade
11:10 AM Panel Discussion <span> <a href="#"></a> </span> Richard Sutton, Doina Precup
11:40 AM Poster Spotlight 2 (Poster Spotlight)
Aaron Sidford, Mengdi Wang, Lin Yang, Yinyu Ye, Zuyue Fu, Zhuoran Yang, Yongxin Chen, Zhaoran Wang, Ofir Nachum, Bo Dai, Ilya Kostrikov, Dale Schuurmans, Ziyang Tang, Yihao Feng, Lihong Li, Denny Zhou, Qiang Liu, Rodrigo Toro Icarte, Ethan Waldie, Toryn Klassen, Rick Valenzano, Margarita Castro, Simon Du, Sham Kakade, Ruosong Wang, Minshuo Chen, Tianyi Liu, Xingguo Li, Zhaoran Wang, Tuo Zhao, Philip Amortila, Doina Precup, Prakash Panangaden, Marc Bellemare
02:00 PM Reinforcement Learning Beyond Optimization (Plenary Talk) Benjamin Van Roy
02:40 PM Learning in structured MDPs with convex cost function: improved regret bounds for inventory management (Plenary Talk) Shipra Agrawal
03:20 PM Poster and Coffee Break 2 (Poster Session)
Karol Hausman, Kefan Dong, Ken Goldberg, Lihong Li, Lin Yang, Lingxiao Wang, Lior Shani, Liwei Wang, Loren Amdahl-Culleton, Lucas Cassano, Marc Dymetman, Marc Bellemare, Marcin Tomczak, Margarita Castro, Marius Kloft, Marius-Constantin Dinu, Markus Holzleitner, Martha White, Mengdi Wang, Michael Jordan, Mihailo Jovanovic, Ming Yu, Minshuo Chen, Moonkyung Ryu, Muhammad Zaheer, Naman Agarwal, Nan Jiang, Niao He, Niko Yasui, Nikos Karampatziakis, Nino Vieillard, Ofir Nachum, Olivier Pietquin, Ozan Sener, Pan Xu, Parameswaran Kamalaruban, Paul Mineiro, Paul Rolland, Philip Amortila, Pierre-Luc Bacon, Prakash Panangaden, Qi Cai, Qiang Liu, Quanquan Gu, Raihan Seraj, Richard Sutton, Rick Valenzano, Robert Dadashi, Rodrigo Toro Icarte, Roshan Shariff, Roy Fox, Ruosong Wang, Saeed Ghadimi, Samuel Sokota, Sean Sinclair, Sepp Hochreiter, Sergey Levine, Sergio Valcarcel Macua, Sham Kakade, Shangtong Zhang, Sheila McIlraith, Shie Mannor, Shimon Whiteson, Shuai Li, Shuang Qiu, Sibon Li, Sid Banerjee, Sitao Luan, Tamer Basar, Thinh Doan, Tianhe (Kevin) Yu, Tianyi Liu, Tom Zahavy, Toryn Klassen, Tuo Zhao, Vicenç Gómez, Vincent Liu, Volkan Cevher, Wesley Suttle, Xiao-Wen Chang, Xiaohan Wei, Xiaotong Liu, Xingguo Li, Xinyi Chen, Xingyou Song, Yao Liu, YiDing Jiang, Yihao Feng, Yilun Du, Yinlam Chow, Yinyu Ye, Yishay Mansour, , Yonathan Efroni, Yongxin Chen, Yuanhao Wang, Bo Dai, Chen-Yu Wei, Harsh Shrivastava, Ryan Zhang, Qinqing Zheng, Satpathi SATPATHI, Xueqing Liu, Andreu Vall
04:20 PM On the Convergence of GTD($\lambda$) with General $\lambda$ (Plenary Talk) Huizhen Yu
05:00 PM Continuous Online Learning and New Insights to Online Imitation Learning (Contributed Talk) Jonathan Lee, Ching-An Cheng, Ken Goldberg, Byron Boots
05:20 PM Logarithmic Regret for Online Control (Contributed Talk) Naman Agarwal, Elad Hazan, Karan Singh
05:40 PM Closing Remarks <span> <a href="#"></a> </span> Bo Dai, Niao He, Nicolas Le Roux, Lihong Li, Dale Schuurmans, Martha White

Author Information

Bo Dai (Google Brain)
Niao He (UIUC)
Nicolas Le Roux (Google)
Lihong Li (Google Research)
Dale Schuurmans (Google Inc.)
Martha White (University of Alberta)

More from the Same Authors