Research map / Reinforcement learning / Offline RL
Provably Efficient Causal Reinforcement Learning with Confounded Observational Data
Lingxiao Wang, Zhuoran Yang, Zhaoran Wang
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 backdoor-adjusted observational data to online value iteration | DOVI · Confounded MDP with partially observed confounders | regret: When the observational data are sufficiently informative upon the adjustments, \Delta_H decreases towards zero | Improved |
| Add frontdoor-adjusted observational data through an observed intermediate state | DOVI+ · Confounded MDP with unobserved confounders and observed intermediate states | regret: When the observational data are sufficiently informative upon the adjustments, \Delta_{1, H} and \Delta_{2, H} are small | Improved |
| Use observational data that are unavailable or uninformative after adjustment | DOVI · Confounded MDP with partially observed confounders | regret: \Delta_H is a logarithmic factor | No clear effect |
| Increase the effective sample size of sufficiently informative adjusted observational data | DOVI · Confounded MDP with partially observed confounders | regret: \Delta_H = \cO(\sqrt{\log(1 + K/(n + d))}) = \cO(\sqrt{K/(n + d)}) | Improved |
Closest papers by meaning
- Confounding Robust Deep Reinforcement Learning: A Causal Approach (NeurIPS 2025 · similarity 0.88)
- Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding (ICLR 2024 · similarity 0.88)
- Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design (ICML 2024 · similarity 0.87)
- Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound (NeurIPS 2025 · similarity 0.87)
- Information-Directed Offline-to-Online Reinforcement Learning (NeurIPS 2026 · similarity 0.87)
- Iteratively Refined Behavior Regularization for Offline Reinforcement Learning (NeurIPS 2024 · 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.
