Understanding On-policy and Off-policy理解 On-policy 与 Off-policy
Who collects the experience, and who learns from it? A note on behavior policies, target policies, SARSA, and Q-learning.谁收集经验，谁从经验中学习？从行为策略与目标策略出发，理解 SARSA 与 Q-learning。
A notebook by Pin QianPin Qian 的开放笔记
Notes, ideas,
and things worth keeping.想法与笔记，
还有值得留下的事。
Learning notes, open questions, and observations from wherever curiosity leads.学习中的笔记，尚未解答的问题，以及好奇心带我遇见的种种。
Selected note精选笔记
Who acts? Who learns?谁在行动，谁在学习？
Who collects the experience, and who learns from it? A note on behavior policies, target policies, SARSA, and Q-learning.谁收集经验，谁从经验中学习？从行为策略与目标策略出发，理解 SARSA 与 Q-learning。
Open the note ↗打开笔记 ↗Policy & experience策略与经验
πBehavior行为策略
τExperience经验
πTarget目标策略
1 / 3