Research map / Reinforcement learning / Offline RL
On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
Thanh Nguyen-Tang, Ming Yin, Sunil Gupta, Svetha Venkatesh, Raman Arora
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 BCP-VI under unique optimality and spanning features once K exceeds k^* | Offline RL with linear function approximation · Linear MDP, OPC, unique optimality and spanning features | sub-optimality: 0 | Improved |
| Set pessimism parameter β to 1 rather than 0 (ablation) | BCP-VI · Linear MDP simulation, H ∈ {20,30,50,80} | sub-optimality | Improved |
| Remove pessimism by setting β = 0 (ablation) | BCP-VI · Linear MDP simulation, H ∈ {20,30,50,80} | sub-optimality | Hurt |
| Use β values in {0, 0.1, 0.2, 0.5, 1, 2} (ablation) | BCP-VI · Linear MDP simulation, H ∈ {20,30,50,80} | sub-optimality | Mixed |
Closest papers by meaning
- Towards Instance-Optimal Offline Reinforcement Learning with Pessimism (NeurIPS 2021 · similarity 0.94)
- Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning (ICLR 2024 · similarity 0.93)
- Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.92)
- Worst-Case Offline Reinforcement Learning with Arbitrary Data Support (NeurIPS 2024 · similarity 0.92)
- A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs (ICML 2024 · similarity 0.91)
- On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage (NeurIPS 2026 · similarity 0.90)
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.
