Research map / Learning theory and algorithms / Sample complexity
Layered State Discovery for Incremental Autonomous Exploration
Liyu Chen, Andrea Tirinzoni, Alessandro Lazaric, Matteo Pirotta
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 layered state discovery plus policy consolidation (LAE) instead of DisCo-based state discovery | autonomous exploration sample complexity · theoretical sample complexity | sample complexity dependence on L: saves a factor of L^2 over DisCo | Improved |
| Add identifiability assumption on layers {K*_j} | LAE · theoretical sample complexity | sample complexity bound: from O~(L S_{L(1+eps)} Gamma A/eps^2) to O~(L S_L A/eps^2) | Improved |
| Replace log S dependence with log S_{L(1+eps)} via state filtering, scaling of confidence bounds, and Monte-Carlo reachability test | LASD+ (LAE) · theoretical sample complexity | dependence on S | Improved |
Closest papers by meaning
- SeeA*: Efficient Exploration-Enhanced A* Search by Selective Sampling (NeurIPS 2024 · similarity 0.86)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.86)
- Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization (ICML 2024 · similarity 0.85)
- Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction (ICML 2024 · similarity 0.84)
- Global Optimality for Constrained Exploration via Penalty Regularization (NeurIPS 2026 · similarity 0.84)
- Scalable Online Exploration via Coverability (ICML 2024 · similarity 0.84)
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.
