Research map / Reinforcement learning / MDPs and planning
Online RL in Linearly $q^\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore
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 which low-range states to skip, then run a linear-MDP learning algorithm on the resulting reduced problem | Online RL in linearly q^π-realizable MDPs · Linearly q^π-realizable episodic MDPs | online interactions: \tilde{\mathcal{O}}\left(H^{11}d^7/\varepsilon^2\right) | Helped |
| Skip low-range states by following a fixed policy until reaching a state with meaningful action-value differences | Linearly q^π-realizable MDPs · Linearly q^π-realizable episodic MDPs | MDP structure | Helped |
Closest papers by meaning
- Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs (NeurIPS 2024 · similarity 0.90)
- Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs (NeurIPS 2024 · similarity 0.89)
- Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\pi$-Realizability and Concentrability (NeurIPS 2024 · similarity 0.89)
- Scalable Policy-Based RL Algorithms for POMDPs (NeurIPS 2025 · similarity 0.89)
- The Power of Resets in Online Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Confident Natural Policy Gradient for Local Planning in $q_\pi$-realizable Constrained MDPs (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.