D-19: Theory of Reinforcement Learning (invited) |
| Session Type: Virtual |
| Time: Monday, November 01, 11:15 - 12:45 |
| Location: Room 3 |
| Virtual Session: Attend on Virtual Platform |
| Session Chairs: Yingbin Liang, The Ohio State University, USA and Shaofeng Zou, University at Buffalo, USA |
| D-19.1: Multi-Agent Off-Policy TDC with Near-Optimal Sample and Communication Complexity |
| Ziyi Chen; University of Utah |
| Yi Zhou; University of Utah |
| Rongrong Chen; University of Utah |
| D-19.2: Is Q-Learning Minimax Optimal? |
| Yuejie Chi; Carnegie Mellon University |
| D-19.3: Towards Understanding A3C: Non-asymptotic Analysis and Linear Speedup |
| Han Shen; Rensselaer Polytechnic Institute |
| Kaiqing Zhang; University of Illinois at Urbana-Champaign |
| Mingyi Hong; University of Minnesota |
| Tianyi Chen; Rensselaer Polytechnic Institute |
| D-19.4: Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process |
| Tianjiao Li; Georgia Institute of Technology |
| Ziwei Guan; The Ohio State University |
| Shaofeng Zou; University at Buffalo, the State University of New York |
| Tengyu Xu; The Ohio State University |
| Yingbin Liang; The Ohio State University |
| Guanghui Lan; Georgia Institute of Technology |