mlsanityData to 7 Oct 2026

A Deep Reinforcement Learning Chatbot

arXiv 1709.02349 ↗First posted 7 Sep 2017cs.CL cs.AI cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than many competing systems. Due to its machine learning architecture, the system is likely to improve with additional data.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2019: 2; 2020: 2; 2021: 7; 2022: 7; 2023: 13; 2024: 3; 2025: 2.

36 papers.

Sort:

By area:

  1. 2019Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialogcited by 283
  2. 2023MiniLLM: On-Policy Distillation of Large Language Modelscited by 129
  3. 2019Imitation Learning from Imperfect Demonstrationcited by 112
  4. 2020Human-centric Dialog Training via Offline Reinforcement Learningcited by 92
  5. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  6. 2020Text Generation by Learning from Demonstrationscited by 64
  7. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  8. 2023Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Reviewcited by 32
  9. 2024Jill Watson: A Virtual Teaching Assistant powered by ChatGPTcited by 24
  10. 2022APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversationscited by 23
  11. 2021A Survey on Deep Reinforcement Learning for Audio-Based Applicationscited by 17
  12. 2022A Mixture-of-Expert Approach to RL-based Dialogue Managementcited by 16
24 more
  1. 2023Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devicescited by 16
  2. 2023Market Concentration Implications of Foundation Modelscited by 15
  3. 2023Building Persona Consistent Dialogue Agents with Offline Reinforcement Learningcited by 13
  4. 2024Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversationscited by 13
  5. 2023Semi-Offline Reinforcement Learning for Optimized Text Generationcited by 12
  6. 2023Reinforcement Learning for Generative AI: A Surveycited by 11
  7. 2022Conversational Agents: Theory and Applicationscited by 8
  8. 2022Dynamic Planning in Open-Ended Dialogue using Reinforcement Learningcited by 8
  9. 2025Echoing: Identity Failures when LLM Agents Talk to Each Othercited by 8
  10. 2023Assessing the efficacy of large language models in generating accurate teacher responsescited by 6
  11. 2021Automatically Exposing Problems with Neural Dialog Modelscited by 5
  12. 2025Bot Wars Evolved: Orchestrating Competing LLMs in a Counterstrike Against Phone Scamscited by 5
  13. 2021Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intentioncited by 4
  14. 2021Amortized Noisy Channel Neural Machine Translationcited by 4
  15. 2022A Systematic Evaluation of Response Selection for Open Domain Dialoguecited by 4
  16. 2024Apollonion: Profile-centric Dialog Agentcited by 4
  17. 2023Offline Reinforcement Learning for Mixture-of-Expert Dialogue Managementcited by 3
  18. 2021Low-Resource Adaptation of Open-Domain Generative Chatbotscited by 2
  19. 2022Intent Recognition in Conversational Recommender Systemscited by 2
  20. 2023Vision-based DRL Autonomous Driving Agent with Sim2Real Transfercited by 2
  21. 2021Dehumanizing Voice Technology: Phonetic & Experiential Consequences of Restricted Human-Machine Interactioncited by 0
  22. 2022Towards Learning Through Open-Domain Dialogcited by 0
  23. 2023Learning a Formality-Aware Japanese Sentence Representationcited by 0
  24. 2023Let's Get Personal: Personal Questions Improve SocialBot Performance in the Alexa Prizecited by 0