2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
MLSP-26: Reinforcement Learning 2 |
| Session Type: Poster |
| Time: Thursday, 10 June, 13:00 - 13:45 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Seung-Jun Kim, University of Maryland, Baltimore County |
| MLSP-26.1: INTRODUCING DEEP REINFORCEMENT LEARNING TO NLU RANKING TASKS |
| Ge Yu; Amazon Inc |
| Emre Barut; Amazon Inc |
| Chengwei Su; Amazon Inc |
| MLSP-26.2: TEMPORAL LINK PREDICTION VIA REINFORCEMENT LEARNING |
| Ye Tao; Peking University |
| Ying Li; Peking University |
| Zhonghai Wu; Peking University |
| MLSP-26.4: A DEEP REINFORCEMENT LEARNING APPROACH TO AUDIO-BASED NAVIGATION IN A MULTI-SPEAKER ENVIRONMENT |
| Petros Giannakopoulos; National and Kapodistrian University of Athens |
| Aggelos Pikrakis; University of Pireaus |
| Yannis Cotronis; National and Kapodistrian University of Athens |
| MLSP-26.5: GLOBAL-LOCALIZED AGENT GRAPH CONVOLUTION FOR MULTI-AGENT REINFORCEMENT LEARNING |
| Yuntao Liu; National University of Defence Technology |
| Yong Dou; National University of Defence Technology |
| Siqi Shen; National University of Defence Technology |
| Peng Qiao; National University of Defence Technology |
| MLSP-26.6: POPS: POLICY PRUNING AND SHRINKING FOR DEEP REINFORCEMENT LEARNING |
| Dor Livne; Ben Gurion University |
| Kobi Cohen; Ben Gurion University |