Research map / Reinforcement learning / Offline RL
Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning
Luofeng Liao, Zuyue Fu, Zhuoran Yang, Yixin Wang, Dingli Ma, Mladen Kolar, 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 |
|---|---|---|---|
| use instrumental-variable estimation instead of ordinary regression for the transition model | IVVI · Parametric linear CMDP-IV (dim 5) | regret: 590.19 -> 14.84 | Improved |
| use instrumental-variable estimation instead of ordinary regression for the transition model | IVVI · Parametric linear CMDP-IV (dim 20) | regret: 2257.49 -> 505.63 | Improved |
| use instrumental-variable estimation instead of ordinary regression for the transition model | IVVI · Nonparametric CMDP-IV (dim 5) | regret: 74.74 -> 35.90 | Improved |
| increase instrument strength (Sigma_z 0.5 -> 1.5) (ablation) | IVVI · Parametric linear CMDP-IV (dim 5) | regret: 14.84 -> 1.44 | Improved |
| increase instrument strength (Sigma_z 0.5 -> 1.5) (ablation) | IVVI · Parametric linear CMDP-IV (dim 20) | regret: 505.63 -> 117.20 | Improved |
| increase instrument strength (Sigma_z 0.5 -> 1.5) (ablation) | IVVI · Nonparametric CMDP-IV (dim 5) | regret: 35.90 -> 19.98 | Improved |
| use general covariance matrices for noise and action (robustness check) (ablation) | IVVI · Nonparametric CMDP-IV (dim 3) | regret: 47.85 -> 13.25 | Improved |
| use general covariance matrices for noise and action (robustness check) (ablation) | IVVI · Parametric linear CMDP-IV (dim 10) | regret: 832.92 -> 100.79 | Improved |
| increase state dimension from 5 to 20 (ablation) | IVVI · Parametric linear CMDP-IV (config III) | regret: 1.44 -> 117.20 | Hurt |
| increase state dimension from 1 to 5 (ablation) | IVVI · Nonparametric CMDP-IV (config III) | regret: 1.73 -> 19.98 | Hurt |
Closest papers by meaning
- Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning (ICML 2024 · similarity 0.89)
- Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning (ICLR 2024 · similarity 0.89)
- Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning (ICLR 2024 · similarity 0.88)
- Horizon Adaptive Offline Policy Learning via Value Stitching (NeurIPS 2026 · similarity 0.88)
- A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and Preconditioning (NeurIPS 2025 · similarity 0.88)
- Iteratively Refined Behavior Regularization for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
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.
