Research map / Reinforcement learning / Offline RL
Stable-Baselines3: Reliable Reinforcement Learning Implementations
Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, Noah Dormann
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 |
|---|---|---|---|
| rewrite OpenAI Baselines-style codebase as SB3 with unit tests, type hints and CI | SB3 · RL library comparison | test coverage (%): 49% -> 95% | Improved |
| maintain an active contributor workflow with PR review | SB3 · RL library comparison | approved PRs (last 6 months): 0 -> 75 | Improved |
| focus on simplicity and reliability rather than scalability and distributed training | SB3 · RL library comparison | approved PRs (last 6 months): 75 vs 222 | Mixed |
Closest papers by meaning
- OGBench: Benchmarking Offline Goal-Conditioned RL (ICLR 2025 · similarity 0.82)
- MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL (ICLR 2025 · similarity 0.81)
- SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores (ICLR 2024 · similarity 0.81)
- OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning (NeurIPS 2024 · similarity 0.81)
- Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning (NeurIPS 2025 · similarity 0.81)
- Offline Safe Reinforcement Learning Using Trajectory Classification (AAAI 2025 · similarity 0.81)
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.
