Research map / Bandits and online learning / RL theory and MDPs
Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Nikki Lijing Kuang, Ming Yin, Mengdi Wang, Yu-Xiang Wang, Yian Ma
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 posterior-sampling Delayed-PSVI/Delayed-LPSVI instead of UCB-based Delayed-UCBVI under long-tail Pareto delays | Delayed-feedback RL in linear MDPs · Synthetic linear MDP, Pareto delay | average return and convergence rate | Improved |
| Use posterior-sampling algorithms instead of Delayed-UCBVI under Multinomial and Poisson delays | Delayed-feedback RL in linear MDPs · Synthetic linear MDP, Multinomial and Poisson delay | average return | Improved |
| Heavy-tailed instead of well-behaved delays for Delayed-UCBVI | Delayed-UCBVI · Synthetic linear MDP | average return | Hurt |
| Replace exact posterior sampling with Langevin Monte Carlo (Delayed-LPSVI vs Delayed-PSVI) | Delayed-PSVI · Linear MDP regret bound | computational cost | Improved |
| Replace exact posterior sampling with LMC | Delayed-PSVI · Linear MDP regret bound | worst-case regret | No clear effect |
Closest papers by meaning
- Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees (NeurIPS 2022 · similarity 0.90)
- Model-based Reinforcement Learning for Continuous Control with Posterior Sampling (ICML 2021 · similarity 0.90)
- Making RL with Preference-based Feedback Efficient via Randomization (ICLR 2024 · similarity 0.89)
- ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling (NeurIPS 2026 · similarity 0.88)
- Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation (NeurIPS 2024 · similarity 0.88)
- Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge (AAAI 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.
