Research map / Reinforcement learning / Visual and representation RL
Exploratory Combinatorial Optimization with 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 |
|---|---|---|---|
| Allow vertex actions to be reversible (ablation) | ECO-DQN · Max-Cut on ER graphs | average cut | Helped |
| Add observations that help exploit reversible actions (ablation) | ECO-DQN · Max-Cut on ER graphs | average cut | Helped |
| Add rewards for reaching previously unseen locally optimal solutions (ablation) | ECO-DQN · Max-Cut on larger ER and BA graphs | approximation ratio | Helped |
| Add rewards for reaching previously unseen locally optimal solutions (ablation) | ECO-DQN · Max-Cut training | training speed and stability | Helped |
| Extend episodes from 2|V| to 4|V| steps | ECO-DQN · ER graphs, |V|=200 | approximation ratio: 0.98±0.01 to 0.99±0.01 | Helped |
| Run 50 episodes from random initial vertex subsets and select the best result | ECO-DQN · Max-Cut on larger or unseen graph distributions | approximation ratio | Helped |
| Train on ER graphs and test on BA graphs, or train on BA and test on ER | ECO-DQN · Max-Cut, graphs up to |V|=500 | approximation ratio | Mixed |
Closest papers by meaning
- Learning Combinatorial Optimization Algorithms over Graphs (NeurIPS 2017 · similarity 0.92)
- Preference Optimization for Combinatorial Optimization Problems (ICML 2025 · similarity 0.88)
- Accelerating Cutting-Plane Algorithms via Reinforcement Learning Surrogates (AAAI 2024 · similarity 0.88)
- Reinforcement learning with combinatorial actions for coupled restless bandits (ICLR 2025 · similarity 0.87)
- Structured Reinforcement Learning for Combinatorial Decision-Making (NeurIPS 2025 · similarity 0.87)
- PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial Optimization (ICLR 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.