Research map / Reinforcement learning / MDPs and planning
Representation Learning for Online and Offline RL in Low-rank MDPs
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 |
|---|---|---|---|
| Interleave representation learning, exploration, and exploitation using UCB bonuses instead of explore-then-commit exploration | Rep-UCB vs. Flambe · Low-rank MDP online RL | sample complexity: \frac{d^7 A^9}{\epsilon^{10} (1-\gamma)^{22}} -> \frac{d^4 A^2}{\epsilon^2 (1-\gamma)^{5} } | Helped |
| Use learned-representation pessimism and plan with reward minus a penalty under partial coverage | Rep-LCB · Low-rank MDP offline RL | suboptimality gap | Helped |
Closest papers by meaning
- Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Provably Efficient CVaR RL in Low-rank MDPs (ICLR 2024 · similarity 0.88)
- RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation (NeurIPS 2024 · similarity 0.88)
- Diffusion Spectral Representation for Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Bridging State and History Representations: Understanding Self-Predictive RL (ICLR 2024 · similarity 0.87)
- Online Laplacian-Based Representation Learning in Reinforcement Learning (ICML 2025 · 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.