mlsanityData to 14 Oct 2026

Deep Reinforcement Learning for Multi-objective Optimization

arXiv 1906.02386 ↗First posted 6 Jun 2019cs.NE math.OCcited by 90

Not on the map. Why?

Cited by 31 in LLM alignment / RLHF / preference optimisation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This study proposes an end-to-end framework for solving multi-objective optimization problems (MOPs) using Deep Reinforcement Learning (DRL), that we call DRL-MOA. The idea of decomposition is adopted to decompose the MOP into a set of scalar optimization subproblems. Then each subproblem is modelled as a neural network. Model parameters of all the subproblems are optimized collaboratively according to a neighborhood-based parameter-transfer strategy and the DRL training algorithm. Pareto optimal solutions can be directly obtained through the trained neural network models. In specific, the multi-objective travelling salesman problem (MOTSP) is solved in this work using the DRL-MOA method by modelling the subproblem as a Pointer Network. Extensive experiments have been conducted to study the DRL-MOA and various benchmark methods are compared with it. It is found that, once the trained model is available, it can scale to newly encountered problems with no need of re-training the model. The solutions can be directly obtained by a simple forward calculation of the neural network; thereby, no iteration is required and the MOP can be always solved in a reasonable time. The proposed method provides a new way of solving the MOP by means of DRL. It has shown a set of new characteristics, e.g., strong generalization ability and fast solving speed in comparison with the existing methods for multi-objective optimizations. Experimental results show the effectiveness and competitiveness of the proposed method in terms of model performance and running time.

Key facts. Cited by 90 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 7; 2023: 7; 2024: 22; 2025: 29; 2026: 15.

90 papers.

Sort:

By area:

  1. 2025Improving Video Generation with Human Feedbackcited by 284
  2. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 256
  3. 2023Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardscited by 243
  4. 2024Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustmentcited by 175
  5. 2023Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimizationcited by 124
  6. 2024Panacea: Pareto Alignment via Preference Adaptation for LLMscited by 80
  7. 2024PAD: Personalized Alignment of LLMs at Decoding-Timecited by 60
  8. 2022Pareto Set Learning for Neural Multi-objective Combinatorial Optimizationcited by 56
  9. 2024GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignmentcited by 54
  10. 2024MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Modelscited by 44
  11. 2024The Perfect Blend: Redefining RLHF with Mixture of Judgescited by 43
  12. 2024Alignment of Diffusion Models: Fundamentals, Challenges, and Futurecited by 35
38 more
  1. 2023Large Language Model for Multi-objective Evolutionary Optimizationcited by 29
  2. 2021Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligencecited by 27
  3. 2025Sotopia-RL: Reward Design for Social Intelligencecited by 24
  4. 2022Imitating Past Successes can be Very Suboptimalcited by 23
  5. 2024Neural Combinatorial Optimization Algorithms for Solving Vehicle Routing Problems: A Comprehensive Survey with Perspectivescited by 23
  6. 2021An Overview and Experimental Study of Learning-based Optimization Algorithms for Vehicle Routing Problemcited by 22
  7. 2025Robust Multi-Objective Preference Alignment with Online DPOcited by 22
  8. 2023Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimizationcited by 21
  9. 2021Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization Problemscited by 20
  10. 2024MAP: Multi-Human-Value Alignment Palettecited by 20
  11. 2025Pareto Set Learning for Multi-Objective Reinforcement Learningcited by 20
  12. 2025Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyondcited by 18
  13. 2022Learning to Solve Vehicle Routing Problems: A Surveycited by 16
  14. 2021Deep Reinforcement Learning for Combinatorial Optimization: Covering Salesman Problemscited by 13
  15. 2023Neural Multi-Objective Combinatorial Optimization with Diversity Enhancementcited by 13
  16. 2025Drift: Decoding-time Personalized Alignments with Implicit User Preferencescited by 13
  17. 2025Multi-Objective Preference Optimization: Improving Human Alignment of Generative Modelscited by 13
  18. 2025Multi-objective Large Language Model Alignment with Hierarchical Expertscited by 13
  19. 2025Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systemscited by 12
  20. 2025Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgmentcited by 11
  21. 2025REMOR: Automated Peer Review Generation with LLM Reasoning and Multi-Objective Reinforcement Learningcited by 11
  22. 2025MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignmentcited by 10
  23. 2025Robust Multi-Objective Controlled Decoding of Large Language Modelscited by 9
  24. 2021MODRL/D-EL: Multiobjective Deep Reinforcement Learning with Evolutionary Learning for Multiobjective Optimizationcited by 8
  25. 2024Personalized Adaptation via In-Context Preference Learningcited by 8
  26. 2022A Survey on Learnable Evolutionary Algorithms for Scalable Multiobjective Optimizationcited by 7
  27. 2025Learning for routing: A guided review of recent developments and future directionscited by 7
  28. 2023Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyMLcited by 6
  29. 2024Multi-objective Deep Learning: Taxonomy and Survey of the State of the Artcited by 6
  30. 2025Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computationcited by 6
  31. 2025Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewardscited by 6
  32. 2023Learning to Branch in Combinatorial Optimization with Graph Pointer Networkscited by 4
  33. 2024Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learningcited by 4
  34. 2024Constrained Multi-objective Optimization with Deep Reinforcement Learning Assisted Operator Selectioncited by 4
  35. 2024Multiobjective Vehicle Routing Optimization with Time Windows: A Hybrid Approach Using Deep Reinforcement Learning and NSGA-IIcited by 4
  36. 2025ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Datacited by 4
  37. 2026AI Alignment Breaks at the Edgecited by 4
  38. 2024Enhancing Vehicle Aerodynamics with Deep Reinforcement Learning in Voxelised Modelscited by 3

50 most cited of 90 All 90 (JSON)