mlsanityData to 7 Oct 2026

Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion

arXiv 2605.31388 ↗First posted 29 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-Objective Reinforcement Learning (MORL) extends standard RL by optimizing policies with respect to multiple, often conflicting, objectives. While max-min MORL has emerged as an effective approach for promoting fairness, its applicability remains limited, particularly when constraints must be incorporated. In this paper, we propose a MORL framework that integrates the max-min criterion with explicit constraint satisfaction. We establish a theoretical foundation for the proposed framework and validate the resulting algorithm through convergence analysis and experiments in tabular settings. We further demonstrate the practical relevance of our approach in simulated building thermal control, multi-objective locomotion control, and greenhouse-gas-emission-aware traffic management. Across these domains, our method effectively balances fairness and constraint satisfaction in multi-objective decision-making.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 66 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

43 of 66 references.

References · 43

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2021Convex optimizationcited by 2,479
  4. 2017Constrained Policy Optimizationcited by 928
  5. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  6. 2014Convex Optimization: Algorithms and Complexitycited by 569
  7. 2018Reward Constrained Policy Optimizationcited by 397
  8. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 240
  9. 2014A Survey of Multi-Objective Sequential Decision-Makingcited by 229
  10. 2019A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptationcited by 166
  11. 2019Constrained Reinforcement Learning Has Zero Duality Gapcited by 144
  12. 2015Taming the Noise in Reinforcement Learning via Soft Updatescited by 125
31 more
  1. 2021OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimationcited by 121
  2. 2024MaxMin-RLHF: Alignment with Diverse Human Preferencescited by 121
  3. 2019IPO: Interior-point Policy Optimization under Constraintscited by 119
  4. 2020Learning to Walk in the Real World with Minimal Human Effortcited by 103
  5. 2018Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimizationcited by 97
  6. 2018Dynamic Weights in Multi-Objective Deep Reinforcement Learningcited by 96
  7. 2022COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimationcited by 69
  8. 2013Projection onto the probability simplex: An efficient algorithm with a simple proof, and an applicationcited by 65
  9. 2020Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewardscited by 60
  10. 2019Reinforcement Learning with Convex Constraintscited by 57
  11. 2022PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithmcited by 51
  12. 2023Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritizationcited by 46
  13. 2020Inverse Constrained Reinforcement Learningcited by 45
  14. 2021State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewardscited by 37
  15. 2022Near-Optimal Sample Complexity Bounds for Constrained MDPscited by 36
  16. 2024Truly No-Regret Learning in Constrained MDPscited by 23
  17. 2022Welfare and Fairness in Multi-objective Reinforcement Learningcited by 20
  18. 2024The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithmcited by 13
  19. 2024Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximationcited by 10
  20. 2022Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probabilitycited by 9
  21. 2022Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshotscited by 9
  22. 2025On Generalization Across Environments In Multi-Objective Reinforcement Learningcited by 8
  23. 2021A Deep Reinforcement Learning Approach for Fair Traffic Signal Controlcited by 7
  24. 2023Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Returncited by 7
  25. 2024An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learningcited by 5
  26. 2025Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spacescited by 5
  27. 2025Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approachcited by 5
  28. 2024Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learningcited by 4
  29. 2024Confidence Aware Inverse Constrained Reinforcement Learningcited by 4
  30. 2020Cooling-Aware Resource Allocation and Load Management for Mobile Edge Computing Systemscited by 1
  31. 2025Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learningcited by 1

Built on by

Not cited yet.