Research map / Reinforcement learning / Visual and representation RL
POMO: Policy Optimization with Multiple Optima for Reinforcement Learning
Yeong-Dae Kwon, Jinho Choo, Byoungjip Kim, Iljoo Yoon, Youngjune Gwon, Seungjai Min
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 |
|---|---|---|---|
| train with POMO (shared multi-start baseline) instead of REINFORCE greedy rollout baseline (ablation) | AM · TSP100 | optimality gap: 3.51% -> 1.07% | Improved |
| train with POMO instead of REINFORCE (ablation) | AM · CVRP100 | gap: 6.72 -> 3.00 | Improved |
| add multiple greedy rollouts from all start nodes at inference (ablation) | POMO · TSP100 | optimality gap: 1.07 -> 0.46 | Improved |
| add x8 instance augmentation at inference (ablation) | POMO · TSP100 | optimality gap: 0.46 -> 0.14 | Improved |
| add x8 instance augmentation at inference (ablation) | POMO · CVRP100 | gap: 0.98 -> 0.32 | Improved |
| add multiple greedy rollouts at inference (ablation) | POMO · KP100 | gap: 0.125 -> 0.006 | Improved |
| add x8 augmentation to REINFORCE-trained AM (ablation) | AM · TSP100 | optimality gap: 3.51 -> 1.67 | Improved |
Closest papers by meaning
- Combinatorial Optimization with Policy Adaptation using Latent Space Search (NeurIPS 2023 · similarity 0.89)
- Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation (NeurIPS 2025 · similarity 0.89)
- Preference Optimization for Combinatorial Optimization Problems (ICML 2025 · similarity 0.89)
- DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization (AAAI 2024 · similarity 0.87)
- Submodular Reinforcement Learning (ICLR 2024 · similarity 0.87)
- Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization (ICML 2025 · 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.
