Research map / Reinforcement learning / Offline RL
Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 validity (occupancy-measure) constraints to the LP instead of behavior regularization | LP-based offline RL with function approximation · theoretical sample complexity | sample complexity rate in n: O(1/n^1/6) to O(1/√n) | Helped |
| Add a lower-bound constraint on the density ratio (sum_a w(s,a)πμ(a|s) ≥ 1−γ) in the minimax formulation | realizability-only minimax LP · theoretical sample complexity | sample complexity rate in n: realizability-only O(1/√n) with gap dependence | Helped |
| Tabular reduction of the proposed constrained LP | tabular MDPs · theoretical sample complexity | dependence on (1-γ): (1-γ)^-1 vs (1-γ)^-3/2 for Rashidinejad et al. 2021 | Helped |
Closest papers by meaning
- Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.92)
- A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs (ICML 2024 · similarity 0.92)
- A Clean Slate for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning (ICLR 2024 · similarity 0.91)
- On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage (NeurIPS 2026 · similarity 0.91)
- Worst-Case Offline Reinforcement Learning with Arbitrary Data Support (NeurIPS 2024 · similarity 0.91)
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.