| Presentation # | 8 |
| Session: | Dialogue |
| Location: | Kallirhoe Hall |
| Session Time: | Thursday, December 20, 10:00 - 12:00 |
| Presentation Time: | Thursday, December 20, 10:00 - 12:00 |
| Presentation: |
Poster
|
| Topic: |
Spoken dialog systems: |
| Paper Title: |
LEARNING GOAL-ORIENTED VISUAL DIALOG VIA TEMPERED POLICY GRADIENT |
| Authors: |
Rui Zhao, Volker Tresp, Siemens & LMU, Germany |
| Abstract: |
Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extensions for policy gradient methods, which are referred to as Tempered Policy Gradients (TPGs). On a recent AI-testbed, i.e., the GuessWhat?! game, we achieve significant improvements with two innovations. The first one is an extension of the state-of-the-art solutions with Seq2Seq and Memory Network structures that leads to an improvement of 7%. The second one is the application of our newly developed TPG methods, which improves the performance additionally by around 5% and, even more importantly, helps produce more convincing utterances. |