user5311361
Reputation: 47
How do I describe optimal policy (pi*) of bellman's equation?
I tried to find what is pi* in many resources like this link. But, I can not find what is pi*. Is V* is same as V_pi*?
Upvotes: 0
Views: 147
Answers (1)
suat
Reputation: 4289
π* is used to represent the "optimal policy". V* and Q* are optimal value functions. Optimal value functions lead to optimal policies.
Have a look at the Section 4.6 at https://web.fe.up.pt/~eol/schaefer/diplom/ReinforcementLearning.htm
Upvotes: 2
Related Questions
- What is the way to understand Proximal Policy Optimization Algorithm in RL?
- Bellman equation
- Why the time complexity of bellman equation is n^3 for the direct solution?
- Relationship between bellman optimal equation and Q-learning
- Objective function in proximal policy optimization
- What is Optimality in Reinforcement Learning?
- What is the policy gradient when multiple actions are possible?
- State value and state action values with policy - Bellman equation with policy
- How is the optimal policy for recurrent utilities calculated?
- Markov decision process - how to use optimal policy formula?