Research map / Reinforcement learning / Policy gradient and actor-critic
Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees
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 |
|---|---|---|---|
| Train the RL policy with awareness of online switching rather than train it standalone | LOMAR versus DRL-OS · MovieLens test, rho=0.4 | AVG: 12.315 -> 12.364 | Helped |
| Train the RL policy with awareness of online switching rather than train it standalone | LOMAR versus DRL-OS · MovieLens test, rho=0.6 | AVG: 11.919 -> 11.990 | Helped |
| Train the RL policy with awareness of online switching rather than train it standalone | LOMAR versus DRL-OS · MovieLens test, rho=0.8 | AVG: 11.524 -> 11.561 | Helped |
| Add online switching to the standalone RL policy | DRL-OS versus DRL · MovieLens | CR: 0.544 -> 0.800 | Helped |
| Use switching-aware training and online switching | LOMAR versus DRL · gMission 100x100 | AVG: 32.938 -> 40.332 | Helped |
| Use switching-aware training and online switching | LOMAR versus DRL · gMission 100x100 | CR: 0.576 -> 0.798 | Helped |
| Use online switching with a standalone RL policy | DRL-OS versus DRL · gMission 100x100 | CR: 0.576 -> 0.794 | Helped |
| Increase the inference robustness parameter rho | LOMAR · gMission 100x100 | AVG: 38.538 -> 40.332 | Mixed |
| Replace pure RL with LOMAR switching | LOMAR versus DRL · Free-disposal matching | CR: 0.623 -> 0.738 | Helped |
| Replace pure RL with LOMAR switching | LOMAR versus DRL · Free-disposal matching | AVG: 8.172 -> 7.764 | Hurt |
Closest papers by meaning
- Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement Learning (ICML 2024 · similarity 0.90)
- Online bipartite matching with imperfect advice (ICML 2024 · similarity 0.90)
- Learning-Augmented Online Bipartite Fractional Matching (NeurIPS 2025 · similarity 0.89)
- DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models (ICML 2025 · similarity 0.88)
- Fairness and Efficiency in Online Class Matching (NeurIPS 2024 · similarity 0.86)
- Beyond the Half Approximation: Fair and Efficient Online Class Matching (NeurIPS 2026 · 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.