Research map / Bandits and online learning / Online convex optimization and games
Information Theoretic Regret Bounds for Online Nonlinear Control
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 |
|---|---|---|---|
| LC3 with posterior-sampling exploration vs random walk and PETS-CEM (no exploration) | LC3 · Maze | success within 50 episodes: first success after 25.0 episodes on average vs never | Helped |
| use ensemble-of-simulators features instead of random Fourier features (ablation) | LC3 · Armhand dexterous manipulation | task success | Helped |
| use neural-network top-layer features instead of ensemble features (ablation) | LC3 · Armhand dexterous manipulation | task success | Hurt |
| fixed random Fourier features on contact-rich dynamics | LC3 · Hopper | reward: 2995.7 (GT-MPPI) vs -1016.5 | Hurt |
Closest papers by meaning
- Online Control of Unknown Time-Varying Dynamical Systems (NeurIPS 2021 · similarity 0.90)
- Naive Exploration is Optimal for Online LQR (ICML 2020 · similarity 0.90)
- Logarithmic Regret for Online Control (NeurIPS 2019 · similarity 0.89)
- Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator (ICLR 2025 · similarity 0.88)
- Regret-Free Reinforcement Learning for Temporal Logic Specifications (ICML 2025 · similarity 0.87)
- A Memory Efficient Unified Algorithm for Online Learning of Linear Dynamical Systems (NeurIPS 2026 · similarity 0.87)
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.