Research map / Bandits and online learning / RL theory and MDPs
Model-based Reinforcement Learning for Continuous Control with Posterior Sampling
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 |
|---|---|---|---|
| Use MPC-PSRL instead of MBPO | model-based continuous control · Reacher (oracle rewards) | episodes to convergence: 20.2 -> 34.6 | Helped |
| Use MPC-PSRL instead of PETS | model-based continuous control · Reacher (oracle rewards) | episodes to convergence: 20.2 -> 26.2 | Helped |
| Use MPC-PSRL instead of MBPO | model-based continuous control · Pusher (oracle rewards) | episodes to convergence: 146.6 -> 209.4 | Helped |
| Use MPC-PSRL instead of PETS | model-based continuous control · Pusher (oracle rewards) | episodes to convergence: 146.6 -> 193.4 | Helped |
| Use MPC-PSRL instead of MBPO | model-based continuous control · Reacher | episodes to convergence: 29.8 -> 54.2 | Helped |
| Use MPC-PSRL instead of MBPO | model-based continuous control · Pusher | episodes to convergence: 151.6 -> 225.0 | Helped |
Closest papers by meaning
- Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces (ICML 2026 · similarity 0.93)
- Why is Posterior Sampling Better than Optimism for Reinforcement Learning? (ICML 2017 · similarity 0.91)
- A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning (NeurIPS 2021 · similarity 0.91)
- Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound (ICML 2020 · similarity 0.90)
- Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees (NeurIPS 2022 · similarity 0.90)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.90)
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.