# Knowledge acquisition for dialogue agents using reinforcement learning on graph representations

arXiv: https://arxiv.org/abs/2406.19500 · HTML: https://mlsanity.com/paper/2406.19500/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 4 of its 22 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Placed in

- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 4 of 4)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Relational Graph Attention Networks](https://mlsanity.com/paper/1904.05811/) (2019)
- [EMISSOR: A platform for capturing multimodal interactions as Episodic Memories and Interpretations with Situated Scenario-based Ontological References](https://mlsanity.com/paper/2105.08388/) (2021)

## Abstract (arXiv)

We develop an artificial agent motivated to augment its knowledge base beyond its initial training. The agent actively participates in dialogues with other agents, strategically acquiring new information. The agent models its knowledge as an RDF knowledge graph, integrating new beliefs acquired through conversation. Responses in dialogue are generated by identifying graph patterns around these new integrated beliefs. We show that policies can be learned using reinforcement learning to select effective graph patterns during an interaction, without relying on explicit user feedback. Within this context, our study is a proof of concept for leveraging users as effective sources of information.