Research map / Reinforcement learning / Policy gradient and actor-critic
Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion
Giseung Park, Hyunyoung Nam, Woohyeon Byeon, Amir Leshem, Youngchul Sung
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the w update (max-min weight learning) (ablation) | Constrained max-min MORL · Building thermal control | minimum return: 626.7 -> 639.8 | Improved |
| add the u update (constraint multiplier learning) (ablation) | Constrained max-min MORL · Building thermal control | cost sum: 200.7 -> 178.7 | Improved |
| add both u and w updates (ablation) | Constrained max-min MORL · Building thermal control | cost sum: 222.0 -> 178.7 | Improved |
| add u update (ablation) | Constrained max-min MORL · Building thermal control | minimum return: 653.5 -> 639.8 | Hurt |
| add constraint handling to max-min | Constrained max-min vs unconstrained max-min · Tabular constrained MOMDPs | optimal value error: 0.325 -> 0.004 | Improved |
| add max-min fairness to constrained max-average | Constrained max-min vs constrained max-average · Tabular constrained MOMDPs | optimal value error: 0.657 -> 0.004 | Improved |
| reduce beta from 0.03 to 0.001 (ablation) | Constrained max-min · Tabular constrained MOMDPs | optimal value error: 0.004 -> 0.021 | Hurt |
| increase beta from 0.03 to 0.1 (ablation) | Constrained max-min · Tabular constrained MOMDPs | optimal value error: 0.004 -> 0.061 | Hurt |
| use ours instead of MA-SAC-L | Constrained max-min vs MA-SAC-L · Building thermal control | minimum return: 620.9 -> 639.8 | Improved |
| use ours instead of MA-SAC-L | Constrained max-min vs MA-SAC-L · MoAnt-v5 | minimum return: 83.0 -> 92.2 | Improved |
| use ours instead of MA-CPGO | Constrained max-min vs MA-CPGO · Traffic signal control | minimum return: -27,830 -> -25,229 | Improved |
Closest papers by meaning
- The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm (ICML 2024 · similarity 0.92)
- Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach (NeurIPS 2025 · similarity 0.90)
- Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning (ICLR 2025 · similarity 0.90)
- On Generalization Across Environments In Multi-Objective Reinforcement Learning (ICLR 2025 · similarity 0.90)
- Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization (NeurIPS 2026 · similarity 0.89)
- Pareto Set Learning for Multi-Objective Reinforcement Learning (AAAI 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
