Installs as a private draft. Your edits and self-improvement runs do not change the published bundle.
Build evals that test whether RL training on task A improved performance on related task B
Build evals that test whether RL training on task A improved performance on related task B
Generalization is the billion-dollar question
Generalization & Continual Learning > Generalization
--- name: "Transfer Eval Design" version: "1.0.0" description: "Build evals that test whether RL training on task A improved performance on related task B" tags: - rl-skills-universe - "generalization-continual-learning" - "generalization" trigger: "transfer-eval-design" --- # Transfer Eval Design Build evals that test whether RL training on task A improved performance on related task B ## Why It Matters Generalization is the billion-dollar question ## Domain **Generalization & Continual Learning** > Generalization