Research map / Reinforcement learning / MDPs and planning
Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver
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 the initial reward-free exploration algorithm to learn a transition model for arbitrary plug-in planning | Linear mixture MDP · Reward-free exploration | episodes: \tilde{O}\left(\frac{d^2 H^4}{\epsilon^2}\right) | Helped |
| Refine uncertainty estimation to measure expected total uncertainty along trajectories, using a maximum total-variance bound | Reward-free Exploration · Linear mixture MDPs, d ≥ H and ε ≤ H/√d | episodes: \tilde{O}(d^2H^4/\epsilon^2) -> \tilde{O}(d^2H^3/\epsilon^2) | Helped |
| Use trajectory-wise uncertainty estimation and maximum total-variance analysis | Reward-free Exploration · Linear mixture MDPs, d ≥ H and ε ≤ H/√d | episodes relative to the lower bound: \tilde{O}(d^2H^3/\epsilon^2); lower bound: \Omega(d^2H^3/\epsilon^2) | No clear effect |
Closest papers by meaning
- Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs (ICML 2023 · similarity 0.94)
- Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation (NeurIPS 2021 · similarity 0.92)
- Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs (NeurIPS 2022 · similarity 0.90)
- Offline-Online Reinforcement Learning for Linear Mixture MDPs (NeurIPS 2026 · similarity 0.88)
- Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs (ICLR 2024 · similarity 0.88)
- Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL (NeurIPS 2025 · similarity 0.88)
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.