Summary of Scalable Multi-objective Reinforcement Learning with Fairness Guarantees Using Lorenz Dominance, by Dimitris Michailidis et al.
Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance
by Dimitris Michailidis, Willem Röpke, Diederik M. Roijers, Sennay Ghebreab, Fernando P. Santos
First submitted to arxiv on: 27 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed algorithm introduces fairness into Multi-Objective Reinforcement Learning (MORL) by utilizing Lorenz dominance to identify equitable reward distributions. The approach, which incorporates flexible fairness preferences through λ-Lorenz dominance, is shown to improve scalability in two large cities, outperforming common multi-objective approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This algorithm helps ensure fairness in MORL by optimizing multiple objectives that involve the preferences of agents or groups. By using Lorenz dominance, it identifies policies with equitable reward distributions and enables flexible fairness preferences through λ-Lorenz dominance. The approach is demonstrated to be effective in a large-scale real-world transport planning environment. |
Keywords
* Artificial intelligence * Reinforcement learning
