On-Policy vs Off-Policy Learning: The Most Misunderstood Distinction in Reinforcement Learning
中文摘要
本文详细解释了强化学习中 On-Policy 与 Off-Policy 的区别，涵盖从 TD 误差到 GRPO 的概念，并在文末提供代数推导。
English Summary
This article explains the distinction between on-policy and off-policy reinforcement learning, covering concepts from TD errors to GRPO with algebraic derivations at the end.
Original Excerpt
From TD errors to GRPO — explained in words, with all the algebra kept in one place at the end, Continue reading on Medium »