EasyDeepLearn

TD vs MC — how they differ in bias-variance.

medium

Answer

  • MC: use full episodic return GtG_{t} → unbiased estimator of V_π, but high variance (many random rewards over full trajectory).
  • TD(0): use rt  +  γr_{t}\; + \;{\gamma} V(s') → biased (bootstrap error from imperfect V estimate) but lower variance (only one reward). n-step and TD(λ) interpolate.
  • Choice: TD when episodes are long or variance dominates, MC when bias is intolerable + episodes short.
Check yourself — multiple choice
  • Random
  • MC: unbiased + high variance (full episode); TD(0): biased + low variance (one-step bootstrap); n-step or TD(λ) interpolate
  • Same thing
  • Only MC

MC unbiased high-var; TD(0) biased low-var; n-step / λ interpolate.

#theory

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions