EasyDeepLearn

TD(λ) — how does it work?

hard

Answer

  • Interpolates between TD(0) (λ=0, low variance biased) and MC (λ=1, unbiased high variance).
  • Uses eligibility traces et(s)e_{t}(s) that decay by γλ each step and increment at visited states.
  • Update: V(s) ← V(s) + α δ e(s) for every s.
  • Online, single-pass, works with function approximation.
  • Foundation of Sutton-Barto RL; GAE is essentially TD(λ) for advantages.
Check yourself — multiple choice
  • Random
  • Interpolate TD(0) and MC via λ; eligibility traces et(s)e_{t}(s) decay γλ; update V(s) ← V + α δ e(s) online; GAE is TD(λ) for advantages
  • Same as MC
  • Not real

TD(λ): eligibility traces + λ interpolation between TD(0) and MC.

#theory

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions