Research map / Reinforcement learning / MDPs and planning
Fairness in Reinforcement Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Impose exact fairness rather than leaving action choices unconstrained | Reinforcement learning in MDPs · MDPs | round complexity: at least Ω(k^n) | Hurt |
| Impose approximate-choice fairness | Reinforcement learning in MDPs · MDPs | round complexity: at least Ω((k/(1+kα))^n) | Hurt |
| Relax fairness from exact or approximate-choice fairness to approximate-action fairness | Reinforcement learning in MDPs · MDPs | round complexity: Ω(k^n) -> \tilde O\left( \frac{n^5 T^*_{\epsilon} k^{\frac{1}{1-\gamma}+5}}{\min\{\alpha^4, \epsilon^4\} \epsilon^2\left | Helped |
| Require approximate-action fairness | Reinforcement learning in MDPs · MDPs | round complexity: at least Ω(k^{1/(1-γ)}) | Hurt |
| Use Fair-E^3 with approximate-action fairness | Reinforcement learning in MDPs · MDPs satisfying standard assumptions | round complexity: \tilde O\left( \frac{n^5 T^*_{\epsilon} k^{\frac{1}{1-\gamma}+5}}{\min\{\alpha^4, \epsilon^4\} \epsilon^2\left(1-\gamma\ | Helped |
Closest papers by meaning
- Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making (ICML 2024 · similarity 0.90)
- A Causal Lens for Learning Long-term Fair Policies (ICLR 2025 · similarity 0.90)
- Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces (ICML 2025 · similarity 0.87)
- FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment (NeurIPS 2025 · similarity 0.86)
- Fair Participation via Sequential Policies (AAAI 2024 · similarity 0.86)
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.