Research map / Reinforcement learning / MDPs and planning
Is Q-Learning Provably Efficient?
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 |
|---|---|---|---|
| Add Bernstein-style UCB exploration to Q-learning | Q-learning · Episodic MDP | regret: ˜O(√H3SAT) to ˜O(√H2SAT) | Helped |
| Use Hoeffding-style UCB exploration instead of ε-greedy | Q-learning · Episodic MDP | regret: Ω(min{T, AH/2}) to O(√H4SATι) | Helped |
| Use learning rate αt = (H + 1)/(H + t) rather than 1/t | Q-learning with UCB exploration · Episodic MDP | regret | Helped |
Closest papers by meaning
- Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP (ICLR 2020 · similarity 0.92)
- Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning (NeurIPS 2021 · similarity 0.91)
- Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs (ICML 2021 · similarity 0.91)
- Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning (ICML 2021 · similarity 0.90)
- Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge (AAAI 2024 · similarity 0.90)
- A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation (NeurIPS 2024 · 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.