Research map / Reinforcement learning / RL from feedback
Fair Policy Aggregation from Standard Policy Optimization
Ezgi Korkmaz
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 |
|---|---|---|---|
| sample from uniform distribution on K* via policy-optimization oracle instead of uniform sampling over occupancy polytope O | max-quantile fairness · Factory monitoring MDP (10 agents, 5 warehouses) | Nash welfare: 0.654 -> 0.701 | Improved |
| same change as above | max-quantile fairness · Factory monitoring MDP (10 agents, 5 warehouses) | Gini coefficient: 0.066 -> 0.087 | Hurt |
| same change as above | max-quantile fairness · Factory monitoring MDP (10 agents, 5 warehouses) | Max quantile q*: 0.999 -> 0.883 | Mixed |
| same change as above | max-quantile fairness · Factory monitoring MDP (10 agents, 5 warehouses) | wall-clock time: approximately 2 hours -> approximately 10 minutes | Improved |
| use max-quantile fairness instead of utilitarian objective | policy aggregation · Factory monitoring MDP (10 agents, 5 warehouses) | Nash welfare: 0.5736 -> 0.701 | Improved |
| use max-quantile fairness instead of egalitarian objective | policy aggregation · Factory monitoring MDP (10 agents, 5 warehouses) | Gini coefficient: 0.2126 -> 0.087 | Improved |
Closest papers by meaning
- Policy Aggregation (NeurIPS 2024 · similarity 0.89)
- FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces (ICML 2025 · similarity 0.88)
- Fair Participation via Sequential Policies (AAAI 2024 · similarity 0.88)
- Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making (ICML 2024 · similarity 0.87)
- Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment (NeurIPS 2025 · 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.
