Quoting Chris Paxton
May 9, 2025
Nice explainer that sets out the boundaries of the RL techniques now dominating progress in AI. The list quoted here neatly describes what the jagged edge of AI will look like for the next little while:
Reinforcement learning is a powerful tool. Right now, though, it’s best used when:
You have a verifiable problem: math, coding, robot grasping
You have a way to generate a ton of data in this domain, but can’t necessarily generate optimal or even good data
The exploration problem is locally tractable, so that when generating this bad data, you will still make some progress
This problem is clearly bounded and is well-posed— think “math olympiad questions” or “walking robot”, not “general-purpose home robot”