Research map / Reinforcement learning / MDPs and planning
Reward-Free Model-Based 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 a Bernstein-type bonus instead of the Hoeffding bonus | UCRL-RFE on Linear Mixture MDPs · Linear Mixture MDPs | exploration episodes for an ε-optimal policy: \tilde \cO(H^5d^2\epsilon^{-2}) -> \tilde \cO(H^4d(H + d)\epsilon^{-2}) | Helped |
| Use the relaxed ℓ1 norm-based optimization (ablation) | UCRL-RFE · Linear Mixture MDPs | exploration episodes for an ε-optimal policy: \tilde \cO(H^5d^2\epsilon^{-2}) -> \tilde \cO(H^5d^3\epsilon^{-2}) | Hurt |
| Use the relaxed ℓ1 norm-based optimization (ablation) | UCRL-RFE+ · Linear Mixture MDPs | exploration episodes for an ε-optimal policy: \tilde \cO(H^4d(H + d)\epsilon^{-2}) -> \tilde \cO(H^4d^2(H + d)\epsilon^{-2}) | Hurt |
| Use a Bernstein-type bonus | UCRL-RFE+ · Linear Mixture MDPs when H ≥ d | exploration episodes for an ε-optimal policy: by a factor of d | Helped |
Closest papers by meaning
- Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs (ICLR 2023 · similarity 0.95)
- Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs (ICML 2023 · similarity 0.94)
- On Reward-Free Reinforcement Learning with Linear Function Approximation (NeurIPS 2020 · similarity 0.93)
- Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver (ICLR 2022 · similarity 0.92)
- Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes (ICML 2022 · similarity 0.92)
- Reward-Free Kernel-Based Reinforcement Learning (ICML 2024 · similarity 0.90)
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.