Research map / Reinforcement learning / MDPs and planning
FLAMBE: Structural Complexity and Representation Learning of 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 |
|---|---|---|---|
| Use simplex factorization and the simplex planner instead of the general low-rank planner | FLAMBE · Simplex-factorized MDP | sample complexity: \tilde{\order}\rbr{ \frac{H^{22}K^9d^7\log(|\Phi||\Upsilon|/\delta)}{\varepsilon^{10}}} -> \tilde{\order}\rbr{\frac{H^{1 | Helped |
| Replace model-based planning with a planner that collects trajectories from the environment | FLAMBE · Reachable simplex-factorized MDP | sample complexity: The algorithm collects \mathrm{poly}(\dlv,H,K,\nicefrac{1}{\etamin},\nicefrac{1}{\varepsilon},\log(|\Phi||\Upsilon|/\del | Mixed |
Closest papers by meaning
- Representation Learning for Online and Offline RL in Low-rank MDPs (ICLR 2022 · similarity 0.92)
- Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure (NeurIPS 2024 · similarity 0.88)
- Diffusion Spectral Representation for Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity (NeurIPS 2024 · similarity 0.87)
- Towards Principled Representation Learning from Videos for Reinforcement Learning (ICLR 2024 · 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.