Training a 4B model to produce 81% faster query plans than Postgres

Training a 4B model to produce 81% faster query plans than Postgres ...or how to make Qwen learn query optimization via agentic reinforcement learning A reinforcement-learning policy update Four RL rollouts commence for a single query. Qwen produces a candidate strategy per rollout and sends it off to Postgres for measurement against its own default plan. Scalar rewards are assigned to each rollou