Research map / Bandits and online learning / RL theory and MDPs
Adaptive Discretization for Model-Based Reinforcement Learning
Sean Sinclair, Tianyu Wang, Gauri Jain, Siddhartha Banerjee, Christina Yu
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 adaptive rather than fixed discretization for model-based RL | UCBVI-style model-based RL · Canonical control problems | convergence and memory usage | Improved |
| Use model-based rather than model-free RL with fixed discretization | RL algorithms · Canonical control problems | performance | Improved |
| Use model-based rather than model-free RL with adaptive discretization | RL algorithms · Canonical control problems | performance | No clear effect |
| Use adaptive rather than fixed discretization | Model-based and model-free RL algorithms · 1 Ambulance, 2 Ambulances, and Oil Problem | running time | Improved |
| Use model-free rather than model-based methods | Adaptive and fixed-discretization algorithms · 1 Ambulance, 2 Ambulances, and Oil Problem | running time | Improved |
Closest papers by meaning
- Model-Based Reinforcement Learning with Value-Targeted Regression (ICML 2020 · similarity 0.90)
- A Unifying View of Optimism in Episodic Reinforcement Learning (NeurIPS 2020 · similarity 0.89)
- A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning (NeurIPS 2021 · similarity 0.89)
- Efficient Exploration in Continuous-time Model-based Reinforcement Learning (NeurIPS 2023 · similarity 0.88)
- Kernel-Based Reinforcement Learning: A Finite-Time Analysis (ICML 2021 · similarity 0.88)
- Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control (ICLR 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.
