Research map / Reinforcement learning / Policy gradient and actor-critic
Replicable Reinforcement Learning
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 randomized statistical-query estimates in phased value iteration | Phased value iteration · GridWorld | samples needed for replicable value functions | Helped |
| Use a smaller rSTAT replicability parameter for a fixed sample size | rPVI · GridWorld | replicability | Helped |
| Add randomized thresholds when deciding which state-action pairs become known | R-max · Episodic exploration | replicability | Helped |
| Require replicability | RL algorithms · Parallel sampling and episodic exploration | sample complexity | Hurt |
Closest papers by meaning
- Replicable Constrained Bandits (NeurIPS 2026 · similarity 0.89)
- On the Computational Landscape of Replicable Learning (NeurIPS 2024 · similarity 0.89)
- Replicable Online Learning (NeurIPS 2025 · similarity 0.88)
- The Power of Resets in Online Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning (NeurIPS 2025 · similarity 0.87)
- Oracle-Efficient Reinforcement Learning for Max Value Ensembles (NeurIPS 2024 · similarity 0.86)
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.