Research map / Reinforcement learning / MDPs and planning
On Reward-Free Reinforcement Learning with Linear Function Approximation
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 linear MDP structure and exploration-driven UCB rewards during exploration | Reward-Free RL for Linear MDPs · Reward-free RL, linear MDP | exploration trajectories for an ε-optimal policy: O\left(d^3H^6\log(dH \delta^{-1}\varepsilon^{-1}) / \varepsilon^2\right) | Helped |
| Rely on linear Q* alone rather than the linear MDP assumption | Reward-free RL · Reward-free RL, linear Q*; deterministic systems | exploration samples required: \Omega(2^H) | Hurt |
| Provide simulator access to query transitions at selected feature-basis pairs | Reward-free RL under linear Q* · Deterministic systems with a simulator | transition queries for an optimal policy: dH | Helped |
| Remove simulator access | Reward-free RL under linear Q* in deterministic systems · Reward-free RL | exploration samples required: dH queries with a simulator; at least Ω(2^H) samples without one | Hurt |
Closest papers by meaning
- Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes (ICML 2022 · similarity 0.95)
- Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation (NeurIPS 2021 · similarity 0.93)
- Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs (ICML 2023 · similarity 0.93)
- Reward-Free Kernel-Based Reinforcement Learning (ICML 2024 · similarity 0.91)
- Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation (NeurIPS 2025 · similarity 0.89)
- Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear 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.