mlsanityData to 14 Oct 2026

Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment

arXiv 2410.11221 ↗First posted 15 Oct 2024cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) is a valuable tool for the creation of AI systems. However it may be problematic to adequately align RL based on scalar rewards if there are multiple conflicting values or stakeholders to be considered. Over the last decade multi-objective reinforcement learning (MORL) using vector rewards has emerged as an alternative to standard, scalar RL. This paper provides an overview of the role which MORL can play in creating pluralistically-aligned AI.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 15 Oct 2024.

Builds on

16 of 30 references.

References · 16

  1. 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Trainingcited by 401
  2. 2024Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Expertscited by 376
  3. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 256
  4. 2023Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardscited by 243
  5. 2014A Survey of Multi-Objective Sequential Decision-Makingcited by 242
  6. 2024A Roadmap to Pluralistic Alignmentcited by 184
  7. 2024Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustmentcited by 175
  8. 2024The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Modelscited by 144
  9. 2021Reward (Mis)design for Autonomous Drivingcited by 104
  10. 2023Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Dutiescited by 97
  11. 2024RLHF from Heterogeneous Feedback via Personalization and Preference Aggregationcited by 74
  12. 2021Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)cited by 55
4 more
  1. 2024Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuningcited by 43
  2. 2024Mapping Social Choice Theory to RLHFcited by 27
  3. 2021MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learningcited by 25
  4. 2022Welfare and Fairness in Multi-objective Reinforcement Learningcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Cultural Palette: Pluralising Culture Alignment via Multi-agent Palettecited by 16
  2. 2025CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectivescited by 10
  3. 2026AI Alignment Breaks at the Edgecited by 4
  4. 2026Overton Pluralistic Reinforcement Learning for Large Language Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI
  2. 2026Objective-Behavior Alignment: Diagnostics for MORL Policy Selection
  3. 2025On Generalization Across Environments In Multi-Objective Reinforcement Learning
  4. 2023Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL
  5. 2026Multi-objective Reinforcement Learning With Augmented States Requires Rewards After Deployment
  6. 2025Variance Reduced Policy Gradient Method for Multi-Objective Reinforcement Learning
  7. 2024Issues with Value-Based Multi-objective Reinforcement Learning: Value Function Interference and Overestimation Sensitivity
  8. 2024Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning