mlsanityData to 14 Oct 2026

An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals

arXiv 2506.03519 ↗First posted 4 Jun 2025cs.CLcited by 2

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Deep Reinforcement Learning (DRL) is widely used in task-oriented dialogue systems to optimize dialogue policy, but it struggles to balance exploration and exploitation due to the high dimensionality of state and action spaces. This challenge often results in local optima or poor convergence. Evolutionary Algorithms (EAs) have been proven to effectively explore the solution space of neural networks by maintaining population diversity. Inspired by this, we innovatively combine the global search capabilities of EA with the local optimization of DRL to achieve a balance between exploration and exploitation. Nevertheless, the inherent flexibility of natural language in dialogue tasks complicates this direct integration, leading to prolonged evolutionary times. Thus, we further propose an elite individual injection mechanism to enhance EA's search efficiency by adaptively introducing best-performing individuals into the population. Experiments across four datasets show that our approach significantly improves the balance between exploration and exploitation, boosting performance. Moreover, the effectiveness of the EII mechanism in reducing exploration time has been demonstrated, achieving an efficient integration of EA and DRL on task-oriented dialogue policy tasks.

Key facts. Cited by 2 papers in the map (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 19 of its 38 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

19 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning31 Jan

Other references · 18

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  4. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  5. 2017Deep Reinforcement Learning that Matterscited by 754
  6. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 411
  7. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  8. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 166
  9. 2018Evolution-Guided Policy Gradient in Reinforcement Learningcited by 83
  10. 2016A User Simulator for Task-Completion Dialoguescited by 57
  11. 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
  12. 2017End-to-End Task-Completion Neural Dialogue Systemscited by 52
6 more
  1. 2018Microsoft Dialogue Challenge: Building End-to-End Task-Completion Dialogue Systemscited by 47
  2. 2022A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learningcited by 30
  3. 2024Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithmscited by 26
  4. 2022ERL-Re2: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representationcited by 14
  5. 2020NROWAN-DQN: A Stable Noisy Network with Noise Reduction and Online Weight Adjustment for Explorationcited by 5
  6. 2017Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisationcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Benchmarking and Learning Real-World Customer Service Dialoguecited by 1
  2. 2025DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual-Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems
  2. 2021Integrating Pretrained Language Model for Dialogue Policy Learning
  3. 2024Enhancing End-to-End Multi-Task Dialogue Systems: A Study on Intrinsic Motivation Reinforcement Learning Algorithms for Improved Training and Adaptability
  4. 2025SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
  5. 2025GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
  6. 2026Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
  7. 2023Deep RL with Hierarchical Action Exploration for Dialogue Generation
  8. 2026Evolutionary System Prompt Learning for Reinforcement Learning in LLMs