papers AI Learner
The Github is limit! Click to go to the new site.

Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient

2019-02-20
Rui Zhao, Volker Tresp

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1807.00737

PDF

http://arxiv.org/pdf/1807.00737


Similar Posts

Comments