mlsanityData to 14 Oct 2026

Towards Goal-Oriented Agents for Evolving Problems Observed via Conversation

arXiv 2401.05822 ↗First posted 11 Jan 2024cs.AI cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

The objective of this work is to train a chatbot capable of solving evolving problems through conversing with a user about a problem the chatbot cannot directly observe. The system consists of a virtual problem (in this case a simple game), a simulated user capable of answering natural language questions that can observe and perform actions on the problem, and a Deep Q-Network (DQN)-based chatbot architecture. The chatbot is trained with the goal of solving the problem through dialogue with the simulated user using reinforcement learning. The contributions of this paper are as follows: a proposed architecture to apply a conversational DQN-based agent to evolving problems, an exploration of training methods such as curriculum learning on model performance and the effect of modified reward functions in the case of increasing environment complexity.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 17 of its 21 references that are in the map. First posted on arXiv 11 Jan 2024.

Builds on

17 of 21 references.

References · 17

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  4. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  5. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  6. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 204
  7. 2018Compositional Attention Networks for Machine Reasoningcited by 183
  8. 2019Interactive Fiction Games: A Colossal Adventurecited by 168
  9. 2020Keep CALM and Explore: Language Models for Action Generation in Text-based Gamescited by 108
  10. 2018Relational Deep Reinforcement Learningcited by 73
  11. 2016A User Simulator for Task-Completion Dialoguescited by 57
  12. 2018Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learningcited by 53
5 more
  1. 2017End-to-End Task-Completion Neural Dialogue Systemscited by 52
  2. 2018Counting to Explore and Generalize in Text-based Gamescited by 36
  3. 2022CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learningcited by 34
  4. 2019Improving Deep Reinforcement Learning in Minecraft with Action Advicecited by 10
  5. 2020Relational-Grid-World: A Novel Relational Reasoning Environment and An Agent Model for Relational Information Extractioncited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimizationcited by 10

Similar, not cited

Close in wording, no citation either way

  1. 2023Chatbots as Problem Solvers: Playing Twenty Questions with Role Reversals
  2. 2026Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
  3. 2025SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
  4. 2024Knowledge acquisition for dialogue agents using reinforcement learning on graph representations
  5. 2024Reinforcement Learning Problem Solving with Large Language Models
  6. 2024Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments
  7. 2025An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals
  8. 2025Continuous Learning Conversational AI: A Personalized Agent Framework via A2C Reinforcement Learning