Research map / Reinforcement learning / Visual and representation RL
Large-State Reinforcement Learning for Hyper-Heuristics
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 |
|---|---|---|---|
| combine the rich 15-feature state representation, ILS-based exploration, and reinforcement learning | LAST-RL · CHeSC 2011 | points: 142.10 -> 166.50 | Helped |
| add ILS-based heuristic-category selection during exploration (ablation) | reinforcement-learning hyper-heuristic · CHeSC 2011 | points: 137.40 -> 166.50 | Helped |
| add reinforcement learning to ILS-based heuristic selection (ablation) | ILS-only hyper-heuristic · CHeSC 2011 | points: 129.25 -> 166.50 | Helped |
| add reinforcement learning to ILS-based heuristic selection (ablation) | ILS-only hyper-heuristic · Bin Packing | points: 27.85 -> 19 | Hurt |
| add ILS-based heuristic-category selection during exploration (ablation) | reinforcement-learning hyper-heuristic · SAT | points: 0.00 -> 24.10 | Helped |
| add reinforcement learning to ILS-based heuristic selection (ablation) | ILS-only hyper-heuristic · VRP | points: 36 -> 34 | Hurt |
| use the rich search-state features instead of only the previous heuristic (ablation) | LAST-RL · Personnel Scheduling | points: 26.0 -> 36.0 | Helped |
| use the rich search-state features instead of only the previous heuristic (ablation) | LAST-RL · Flowshop | points: 20.0 -> 28.5 | Helped |
| use the rich search-state features instead of only the previous heuristic (ablation) | LAST-RL · TSP | points: 17.9 -> 24.9 | Helped |
| use the rich search-state features instead of only the previous heuristic (ablation) | LAST-RL · VRP | points: 36 -> 34 | No clear effect |
| use LAST-RL for one-hour personnel scheduling optimization | Bus Driver Scheduling · Bus Driver Scheduling | objective value | Helped |
| apply LAST-RL to the full Minimum Shift Design problem | Minimum Shift Design hyper-heuristics · Minimum Shift Design, full problem | deviation from lower bound | Helped |
Closest papers by meaning
- Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning (ICML 2025 · similarity 0.87)
- HYPRL: Reinforcement Learning of Control Policies for Hyperproperties (NeurIPS 2025 · similarity 0.86)
- Oracle-Efficient Reinforcement Learning for Max Value Ensembles (NeurIPS 2024 · similarity 0.86)
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
- Going Beyond Heuristics by Imposing Policy Improvement as a Constraint (NeurIPS 2024 · similarity 0.86)
- Towards General-Purpose Model-Free Reinforcement Learning (ICLR 2025 · similarity 0.85)
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.