Research map / Reinforcement learning / MDPs and planning
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
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 OOM-UCB with optimistic exploration and observable-operator confidence sets | Undercomplete episodic finite POMDPs · Undercomplete episodic finite POMDPs | sample complexity for an ε-optimal policy: poly(H, S, A, O, α^{-1})/ε^2 | Helped |
| Use the specialized algorithm for deterministic transitions | Deterministic-transition POMDPs · Deterministic-transition POMDPs | sample complexity for an ε-optimal policy: O(H^2SA log(HSA/p)/(min{ε/(√O H),ξ})^2) | Helped |
| Allow more latent states than observations | POMDP reinforcement learning · Overcomplete POMDPs | sample complexity: Ω(A^{H-1}) | Hurt |
| Remove the lower bound on the minimum singular value of the observation matrices | POMDP reinforcement learning · Undercomplete POMDPs | sample complexity: Ω(A^{H-1}) | Hurt |
Closest papers by meaning
- Learning in Observable POMDPs, without Computationally Intractable Oracles (NeurIPS 2022 · similarity 0.92)
- Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight (ICLR 2024 · similarity 0.92)
- Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning (ICML 2024 · similarity 0.91)
- Model-based Reinforcement Learning for Confounded POMDPs (ICML 2024 · similarity 0.91)
- A Policy Gradient Method for Confounded POMDPs (ICLR 2024 · similarity 0.89)
- Sequential Monte Carlo for Policy Optimization in Continuous POMDPs (NeurIPS 2025 · 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.