Research map / Reinforcement learning / Offline RL
Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
Shengpu Tang, Maggie Makar, Michael Sjoding, Finale Doshi-Velez, Jenna Wiens
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 linear factored Q-decomposition instead of combinatorial Q-function | Fitted Q-iteration · Sepsis simulator (small sample sizes <5000) | policy value | Improved |
| use linear factored Q-decomposition instead of combinatorial Q-function | Fitted Q-iteration · Sepsis simulator (large sample sizes) | policy value | Hurt |
| use factored Q-decomposition when behavior policy undersamples optimal action (rho=0) | Fitted Q-iteration · Sepsis simulator | policy value | Improved |
| use factored BCQ instead of combinatorial BCQ | discrete BCQ · MIMIC-III sepsis test set | WIS policy value at same ESS | Improved |
| use factored BCQ instead of combinatorial BCQ | discrete BCQ · MIMIC-III sepsis test set | agreement with clinician policy | No clear effect |
Closest papers by meaning
- BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces (NeurIPS 2025 · similarity 0.88)
- In-Context Reinforcement Learning for Variable Action Spaces (ICML 2024 · similarity 0.87)
- On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage (NeurIPS 2026 · similarity 0.87)
- Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding (ICLR 2024 · similarity 0.86)
- Efficient Off-Policy Learning for High-Dimensional Action Spaces (ICLR 2025 · similarity 0.86)
- REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes (ICLR 2024 · 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.
