Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems
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 |
|---|---|---|---|
| Frequent-update TS (new parameter sampled each step) instead of lazy episode-based updates | Thompson sampling for LQ control · Linear quadratic control, n=1 | cumulative regret order: O(T^{2/3}) to O(sqrt(T)) | Helped |
| Novel bound on regret from policy switches via expected absolute deviation of Riccati solution under TS distribution | Thompson sampling for LQ control · Linear quadratic control, any dimension | cumulative gap regret Rgap | Helped |
| Extension of the optimal-probability lower bound from n=1 to multi-dimensional systems | Thompson sampling for LQ control · Multi-dimensional LQ systems (numerical) | probability of being optimistic p_opt | No clear effect |
Closest papers by meaning
- Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning (NeurIPS 2023 · similarity 0.92)
- No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes (NeurIPS 2025 · similarity 0.90)
- Society of Agents: Regret Bounds of Concurrent Thompson Sampling (NeurIPS 2022 · similarity 0.90)
- Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces (ICML 2026 · similarity 0.90)
- Optimistic posterior sampling for reinforcement learning: worst-case regret bounds (NeurIPS 2017 · similarity 0.90)
- Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback (ICML 2025 · 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.