Pedro Domingos claims reinforcement learning is basically useless

Pedro Domingos cited new research suggesting supervised-learning alternatives can match RL results, arguing reinforcement learning solves nothing beyond better generalization and mocking researchers who relabel failed methods as RL.

2026-10-23 ~ 2026-10-23 · 3 related posts

• Domingos Cites New Result Claiming RL Is 'Basically Useless' vs Supervised Learning — pmddomingos · 2026-10-23
• Pedro Domingos argues RL solves nothing that better generalization can't — pmddomingos · 2026-10-23
• Pedro Domingos: when your pet technique fails, just rename something else as it — pmddomingos · 2026-10-23