Name
Title | ||
|---|---|---|
Deep Reinforcement Learning with a Combinatorial Action Space for Predicting and Tracking Popular Discussion Threads. |
Abstract | ||
|---|---|---|
We introduce an online popularity prediction and tracking task as a benchmark task for reinforcement learning with a combinatorial, natural language action space. A specified number of discussion threads predicted to be popular are recommended, chosen from a fixed window of recent comments to track. Novel deep reinforcement learning architectures are studied for effective modeling of the value function associated with actions comprised of interdependent sub-actions. The proposed model, which represents dependence between sub-actions through a bi-directional LSTM, gives the best performance across different experimental configurations and domains, and it also generalizes well with varying numbers of recommendation requests. |
Year | Venue | Field |
|---|---|---|
2016 | arXiv: Computation and Language | Interdependence,Computer science,Popularity,Thread (computing),Bellman equation,Natural language,Artificial intelligence,Machine learning,Reinforcement learning |
DocType | Volume | Citations |
Journal | abs/1606.03667 | 0 |
PageRank | References | Authors |
0.34 | 17 | 7 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ji He | 1 | 1 | 1.38 |
| Mari Ostendorf | 2 | 2462 | 348.75 |
| Xiaodong He | 3 | 3858 | 190.28 |
| Jianshu Chen | 4 | 883 | 52.94 |
| Jianfeng Gao | 5 | 5729 | 296.43 |
| Lihong Li | 6 | 2390 | 128.53 |
| Deng, Li | 7 | 9691 | 728.14 |