Research map / Reinforcement learning / Visual and representation RL
Discovering Options for Exploration by Minimizing Cover Time
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 8 Covering options instead of using Eigenoptions | Option discovery on four-room · four-room | Expected Cover Time: 695.9 -> 672.0 | Helped |
| Add 8 Covering options instead of using no options | Option discovery on four-room · four-room | Expected Cover Time: 1094.8 -> 672.0 | Helped |
| Add 8 Covering options instead of using Eigenoptions | Option discovery on 9x9 grid · 9x9 grid | Expected Cover Time: 261.5 -> 258.6 | Helped |
| Add 8 Covering options instead of using no options | Option discovery on 9x9 grid · 9x9 grid | Expected Cover Time: 460.5 -> 258.6 | Helped |
| Increase the number of Covering options (ablation) | Q-learning with Covering options · four-room | accumulated reward | Helped |
| Generate options online and add them during learning | Q-learning with Covering options · Parr's maze | goal discovery | Helped |
Closest papers by meaning
- Exploration in Reinforcement Learning with Deep Covering Options (ICLR 2020 · similarity 0.94)
- Scalable Online Exploration via Coverability (ICML 2024 · similarity 0.89)
- Reward-Free Exploration for Reinforcement Learning (ICML 2020 · similarity 0.89)
- 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)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · 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.