🛠️ Steven Gong

Search

SearchSearch

Aug 16, 2025, 1 min read

TD-Lambda

Eligibility Trace

Eligibility traces are one of the basic mechanisms of reinforcement learning. They unity and generalize TD and Monte Carlo methods.

Frequency heurisitic: assign credit to most frequent states Recency heurisitic: assign credit to most recent states

Eligibility traces combine both herusitics.

E0​(s)=0 Et​(s)=γλEt−1​(s)+1(St​=s)

https://www.youtube.com/watch?v=PnHCvfgC_ZA&list=PLzuuYNsE1EZAXYR4FJ75jcJseBmo4KQ9-&index=4

Graph View

Backlinks

  • Reinforcement Learning (RL)
  • Temporal-Difference Learning (TD Learning)

Created with Quartz, © 2025

  • Blog
  • LinkedIn
  • Twitter
  • GitHub