Research map / Reinforcement learning / Policy gradient and actor-critic
Quasi-optimal Reinforcement Learning with Continuous Actions
Yuhan Li, Wenzhuo Zhou, Ruoqing Zhu
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 |
|---|---|---|---|
| Use quasi-optimal action-region screening instead of the compared policy methods | Continuous-action RL on OhioT1DM · OhioT1DM patient-level policy improvement | discounted return improvement | Mixed |
| Use quasi-optimal action-region screening | OhioT1DM dose recommendation · Risky-state transitions | safe transition proportion: 82.2% vs 67.3% (IQN); 82.2% vs 44.6% (SAC) | Improved |
| Select the proximal parameter μ by cross-validation (ablation) | Quasi-optimal learning · Synthetic environments | discounted return | Improved |
| Use quasi-optimal action-region screening rather than an infinite-support Gaussian policy | Continuous-action RL · Synthetic environments I–IV | discounted return | Improved |
| Use quasi-optimal action-region screening rather than SAC | Continuous-action RL · Synthetic environments I–IV | left-tail risk of discounted return | Improved |
Closest papers by meaning
- Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes (NeurIPS 2019 · similarity 0.86)
- On the Challenges of Using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects (AAAI 2023 · similarity 0.86)
- Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies (NeurIPS 2025 · similarity 0.86)
- Fat-to-Thin Policy Optimization: Offline Reinforcement Learning with Sparse Policies (ICLR 2025 · similarity 0.86)
- Position: Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination (ICML 2024 · similarity 0.85)
- EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes (NeurIPS 2024 · similarity 0.84)
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.
