Universal evaluation layer for standard RL environments. Measures what an agent learned - not just how much reward it accumulated.
-
Updated
May 20, 2026 - Python
Universal evaluation layer for standard RL environments. Measures what an agent learned - not just how much reward it accumulated.
kimiflow — Claude Code + Codex plugin for codebase mapping, gated feature/fix flows, token-cheap learning memory, and Obsidian Vault MCP setup.
To associate your repository with the learning-quality topic, visit your repo's landing page and select "manage topics."