Research map / Bandits and online learning / RL theory and MDPs
Model-free Posterior Sampling via Learning Rate Randomization
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 RandQL (randomized learning rates) instead of OptQL (bonus-based Q-learning) | model-free tabular RL · 10x10 grid-world, H=50, eps=0.2 | cumulative regret | Helped |
| Use model-based UCBVI instead of RandQL | tabular RL · 10x10 grid-world, H=50, eps=0.2 | cumulative regret | Helped |
| Use model-based PSRL instead of RandQL | tabular RL · 10x10 grid-world, H=50, eps=0.2 | cumulative regret | Helped |
| Use Greedy-UCBVI (one-step planning with full backup) instead of RandQL | tabular RL · 10x10 grid-world, H=50, eps=0.2 | cumulative regret | Helped |
| Use RandQL instead of model-based methods for computation | tabular RL · 10x10 grid-world, H=50, eps=0.2 | time and space complexity | Helped |
Closest papers by meaning
- Q-learning with Posterior Sampling (ICLR 2026 · similarity 0.91)
- Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning (NeurIPS 2021 · similarity 0.90)
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.89)
- Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation (NeurIPS 2024 · similarity 0.88)
- No-Regret Reinforcement Learning in Smooth MDPs (ICML 2024 · similarity 0.88)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 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.