# Ensemble-Based Deep Reinforcement Learning for Chatbots

arXiv: https://arxiv.org/abs/1908.10422 · HTML: https://mlsanity.com/paper/1908.10422/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2019.

## Built on by (most cited first, 11 of 11)

- [Ensemble deep learning: A review](https://mlsanity.com/paper/2104.02395/) (2021)
- [Rewarding Chatbots for Real-World Engagement with Millions of Users](https://mlsanity.com/paper/2303.06135/) (2023)
- [A Literature Survey of Recent Advances in Chatbots](https://mlsanity.com/paper/2201.06657/) (2022)
- [A Survey on Deep Reinforcement Learning for Audio-Based Applications](https://mlsanity.com/paper/2101.00240/) (2021)
- [Ensemble Reinforcement Learning: A Survey](https://mlsanity.com/paper/2303.02618/) (2023)
- [AI-Enabled Conversational Journaling for Advancing Parkinson's Disease Symptom Tracking](https://mlsanity.com/paper/2503.03532/) (2025)
- [Improving Customer Service Chatbots with Attention-based Transfer Learning](https://mlsanity.com/paper/2111.14621/) (2021)
- [Towards Learning Through Open-Domain Dialog](https://mlsanity.com/paper/2202.03040/) (2022)
- [Incorporating Rivalry in Reinforcement Learning for a Competitive Game](https://mlsanity.com/paper/2208.10327/) (2022)
- [A Conditional Generative Chatbot using Transformer Model](https://mlsanity.com/paper/2306.02074/) (2023)
- [Assistive Chatbots for healthcare: a succinct review](https://mlsanity.com/paper/2308.04178/) (2023)

## Abstract (arXiv)

Trainable chatbots that exhibit fluent and human-like conversations remain a big challenge in artificial intelligence. Deep Reinforcement Learning (DRL) is promising for addressing this challenge, but its successful application remains an open question. This article describes a novel ensemble-based approach applied to value-based DRL chatbots, which use finite action sets as a form of meaning representation. In our approach, while dialogue actions are derived from sentence clustering, the training datasets in our ensemble are derived from dialogue clustering. The latter aim to induce specialised agents that learn to interact in a particular style. In order to facilitate neural chatbot training using our proposed approach, we assume dialogue data in raw text only -- without any manually-labelled data. Experimental results using chitchat data reveal that (1) near human-like dialogue policies can be induced, (2) generalisation to unseen data is a difficult problem, and (3) training an ensemble of chatbot agents is essential for improved performance over using a single agent. In addition to evaluations using held-out data, our results are further supported by a human evaluation that rated dialogues in terms of fluency, engagingness and consistency -- which revealed that our proposed dialogue rewards strongly correlate with human judgements.