Research map / Reinforcement learning / MDPs and planning
Represent to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency
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 |
|---|---|---|---|
| Learn per-step low-rank features and assemble them into a history embedding using Bellman operators, with optimistic planning | Embed to Control (ETC) · Low-rank POMDP with infinite observation and state spaces | sample complexity (iterations T): \(T = \cO\bigl(\gamma^2\cdot \nu^4\cdot d^2\cdot w^2_{\mathfrak{E}}\cdot H^2\cdot A^{2(2k+\ell)}\cdot(k+\ell)\cdot \log( | Helped |
Closest papers by meaning
- Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning (ICML 2024 · similarity 0.91)
- Bridging State and History Representations: Understanding Self-Predictive RL (ICLR 2024 · similarity 0.89)
- Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight (ICLR 2024 · similarity 0.87)
- Diffusion Spectral Representation for Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy (NeurIPS 2024 · similarity 0.87)
- Towards Principled Representation Learning from Videos for Reinforcement Learning (ICLR 2024 · similarity 0.86)
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.