Research map / Reinforcement learning / MDPs and planning
Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems
Eric Yang Yu, Zhizhen Qin, Min Kyung Lee, Sicun Gao
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 |
|---|---|---|---|
| Use advantage regularization for fairness instead of greedy PPO without fairness constraints | PPO · Attention allocation | reward | Improved |
| Use advantage regularization for fairness instead of greedy PPO without fairness constraints | PPO · Attention allocation | fairness violation | Improved |
| Increase the number of sites to create the harder environment | Attention allocation A-PPO · Harder attention allocation | reward | Improved |
| Use advantage regularization rather than reward-only fairness constraints | PPO · Harder attention allocation | fairness violation | Improved |
| Replace the purely greedy human-designed policy with policy optimization | Attention allocation · Harder attention allocation | reward | Improved |
| Use advantage regularization rather than reward-only fairness constraints | PPO · Credit approval | profit | Improved |
| Use A-PPO instead of the oracle-informed equality-of-opportunity policy | Credit approval · Credit approval | profit | Improved |
| Add fairness constraints to PPO (ablation) | PPO · Credit approval | profit | Improved |
| Use advantage regularization instead of reward-only fairness constraints | PPO · Infectious disease control | reward | No clear effect |
| Use advantage regularization instead of reward-only fairness constraints | PPO · Infectious disease control | fairness violation | No clear effect |
| Use PPO with fairness constraints instead of human-designed baseline policies | PPO · Infectious disease control | reward | Improved |
| Use PPO with fairness constraints instead of human-designed baseline policies | PPO · Infectious disease control | fairness violation | Improved |
Closest papers by meaning
- Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate (ICML 2024 · similarity 0.91)
- A Causal Lens for Learning Long-term Fair Policies (ICLR 2025 · similarity 0.91)
- Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making (ICML 2024 · similarity 0.89)
- Long-Term Fair Decision Making through Deep Generative Models (AAAI 2024 · similarity 0.87)
- Fair Off-Policy Learning from Observational Data (ICML 2024 · similarity 0.87)
- Fair Participation via Sequential Policies (AAAI 2024 · similarity 0.87)
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.
