Reinforcement Learning

Behavior Policy VS Target Policy

Naranjito 2024. 10. 6. 23:16
  • Behavior Policy

 

Acting to get the following state.

That is, taking action and getting the next state.

Action for transition.

 

  • Target Policy

 

PDF required to create a Temporary Difference.

 

  • On Policy(Policy) VS Off Policy

 

 

 

 

 

저작자표시

'Reinforcement Learning' 카테고리의 다른 글

Monte-carlo VS Temporal Difference  (0) 2024.10.06
Markov Decision Process, State value function, Action value function, Optimal policy, Bellman equation  (0) 2024.09.22
Q-Learning, Greedy action, Q-Value, Exploration, ϵ-greedy, epsilon-greedy, Exploitation, Discount factor, Q-update  (0) 2024.09.19

'Reinforcement Learning'의 다른글

  • 현재글Behavior Policy VS Target Policy

관련글

티스토리툴바