Research map / Reinforcement learning / MDPs and planning
Operator Theory-Driven Autoformulation of MDPs for Control of Queueing Systems
Victor Baillet, Yuanzhang Xiao, Nicolás Astorga, Mihaela van der Schaar
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 |
|---|---|---|---|
| add syntax check (with solver feedback) to MCTS (ablation) | MCTS · Queueing autoformulation (36 problems) | accuracy at 12 rollouts: 41.6% -> 83.3% | Improved |
| add solver feedback to MCTS without syntax check (ablation) | MCTS · Queueing autoformulation (36 problems) | accuracy at 12 rollouts: 16.0% -> 41.6% | Improved |
| add solver feedback to MCTS without syntax check at 1 rollout (ablation) | MCTS · Queueing autoformulation (36 problems) | accuracy at 1 rollout: 11.0% -> 8.3% | Hurt |
| replace CoT with MCTS under SF and SC (ablation) | targeted-prompt pipeline · Queueing autoformulation (36 problems) | accuracy at 12 rollouts: 75.2% -> 83.3% | Improved |
| replace GPT-4o targeted prompts with MCTS under SF and SC (ablation) | targeted-prompt pipeline · Queueing autoformulation (36 problems) | accuracy at 12 rollouts: 72.0% -> 83.3% | Improved |
| split single prompt into targeted prompts (GPT-4o, w. SF) (ablation) | GPT-4o · Queueing autoformulation (36 problems) | accuracy at 12 rollouts: 0% -> 8.3% | Improved |
| add CoT to single-prompt GPT-4o (ablation) | GPT-4o · Queueing autoformulation (36 problems) | accuracy at 12 rollouts: 0% -> 2.7% | No clear effect |
| add syntax check to targeted GPT-4o prompts (ablation) | GPT-4o targeted prompts · Queueing autoformulation (36 problems) | accuracy at 12 rollouts: 8.3% -> 72.0% | Improved |
| increase MCTS rollouts from 1 to 12 (ablation) | MCTS (w SF & SC) · Queueing autoformulation (36 problems) | accuracy: 63.8% -> 83.3% | Improved |
| reformulate with modified departure operator so uniformization is state-independent | operator graph · Example 1 | structure identification | Improved |
Closest papers by meaning
- Autoformulation of Mathematical Optimization Models Using LLMs (ICML 2025 · similarity 0.84)
- Efficient Value Iteration for s-rectangular Robust Markov Decision Processes (ICML 2024 · similarity 0.84)
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.83)
- Enhancing Decision Making Through the Integration of Large Language Models and Operations Research Optimization (AAAI 2025 · similarity 0.83)
- QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers (NeurIPS 2024 · similarity 0.82)
- SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes (NeurIPS 2025 · similarity 0.82)
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.
