English

Towards Goal-Oriented Agents for Evolving Problems Observed via Conversation

Artificial Intelligence 2024-01-12 v1 Computation and Language

Abstract

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.

Keywords

Cite

@article{arxiv.2401.05822,
  title  = {Towards Goal-Oriented Agents for Evolving Problems Observed via Conversation},
  author = {Michael Free and Andrew Langworthy and Mary Dimitropoulaki and Simon Thompson},
  journal= {arXiv preprint arXiv:2401.05822},
  year   = {2024}
}

Comments

15 pages, 7 figures

R2 v1 2026-06-28T14:14:09.259Z