Research map / Learning theory and algorithms / Sample complexity
Sample-Optimal Parametric Q-Learning Using Linearly Additive Features
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 OPPQ-Learning with anchor state-action pairs, confidence bounds, monotonicity preservation, and variance reduction instead of basic PPQ-Learning | Parametric Q-learning for feature-based MDPs · Feature-based MDP, generative model | sample transitions: (1-\gamma)^{-4} | Helped |
| Use anchor state-action pairs to preserve monotonicity and control error accumulation | OPPQ-Learning · Feature-based MDP, generative model | sample transitions: K/(1-\gamma)^3 | Helped |
Closest papers by meaning
- Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge (AAAI 2024 · similarity 0.87)
- Optimal Sample Complexity for Average Reward Markov Decision Processes (ICLR 2024 · similarity 0.87)
- Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process (NeurIPS 2024 · similarity 0.86)
- Near-Optimal Sample Complexity for MDPs via Anchoring (ICML 2025 · similarity 0.86)
- Finding good policies in average-reward Markov Decision Processes without prior knowledge (NeurIPS 2024 · similarity 0.86)
- Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
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.