# Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient

arXiv: https://arxiv.org/abs/1807.00737 · HTML: https://mlsanity.com/paper/1807.00737/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2018.

## Built on by (most cited first, 3 of 3)

- [Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser](https://mlsanity.com/paper/2109.02297/) (2021)
- [Modeling Explicit Concerning States for Reinforcement Learning in Visual Dialogue](https://mlsanity.com/paper/2107.05250/) (2021)
- [Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene](https://mlsanity.com/paper/2203.08362/) (2022)

## Abstract (arXiv)

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.