Research map / Reinforcement learning / MDPs and planning
Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling
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 |
|---|---|---|---|
| Use online sensitivity sampling to trigger infrequent policy updates | LPO · General function approximation (theoretical) | sample complexity: \widetilde{O}\left(\frac{\text{poly}(d)}{\varepsilon^8}\right) -> \widetilde{O}\left(\frac{{d}^3}{(1-\gamma)^{8} \vareps | Helped |
| Reduce policy update invocations from O(N) to O(poly(log N)) using lazy updates | LPO · General function approximation (theoretical) | policy update invocations: O(N) -> O(\text{poly}(\log N)) | Helped |
| Reuse Monte Carlo samples with trajectory-level importance sampling | LPO Policy Update · Policy evaluation within an optimistic MDP | environment interactions: K -> \lceil\frac{K}{\kappa}\rceil | Helped |
Closest papers by meaning
- Generalized Proximal Policy Optimization with Sample Reuse (NeurIPS 2021 · similarity 0.91)
- Ranking Policy Gradient (ICLR 2020 · similarity 0.90)
- Generalizable Policy Improvement via Reinforcement Sampling (Student Abstract) (AAAI 2024 · similarity 0.90)
- Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems (NeurIPS 2025 · similarity 0.89)
- Learning Optimal Deterministic Policies with Stochastic Policy Gradients (ICML 2024 · similarity 0.89)
- Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality (NeurIPS 2024 · similarity 0.89)
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.