Minari Introduces Standardized Infrastructure for Collaborative RL Datasets
A new paper presents Minari, infrastructure designed to make offline reinforcement learning datasets easier to share, addressing inconsistent formats and poor documentation across benchmarks.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-17 05:00 · arXiv cs.LG
Minari: Infrastructure for Collaborative Reinforcement Learning Datasets