Research map / Reinforcement learning / Visual and representation RL
Fast active learning for pure exploration in reinforcement learning
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 exploration bonuses scaling with 1/n rather than the standard 1/√n | OurAlgorithmRF · Reward-free exploration | sample complexity upper bound dependence on horizon H: improves the bound by a factor of H | Helped |
| Use an accessible upper bound on simple regret for stopping and policy prediction | OurAlgorithmBPI · Best-policy identification | sample complexity upper bound: H^4SA -> H^3SA | Helped |
| Replace random recommendation from regret-minimization with a data-dependent prediction | BPI · Best-policy identification | sample complexity dependence on δ: 1/δ^2 -> log(1/δ) | Helped |
Closest papers by meaning
- Reward-Free Exploration for Reinforcement Learning (ICML 2020 · similarity 0.91)
- Improved Bounds for Reward-Agnostic and Reward-Free Exploration (ICML 2026 · similarity 0.90)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.90)
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.88)
- Improving Intrinsic Exploration by Creating Stationary Objectives (ICLR 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.