Dating is just deep RL: crank the patience, obsessively stare at your policy entropy

k7agar · x · 2026-10-26

An ML double-entendre joke: "having a girlfriend is just about increasing patience and obsessively staring at her selfies," followed by the punchline — "deep reinforcement learning is just about increasing the batch size and obsessively staring at your policy entropy." Classic ML-training-term wordplay.

Original post →

More from Fun

Fun channel →