What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator

Zhaopeng Meng
Zhaopeng Meng
Daniel Graves
Daniel Graves
Dong Li
Dong Li
Yaodong Yang
Yaodong Yang
Cited by: 0|Bibtex|Views21|Links

Abstract:

The value function lies in the heart of Reinforcement Learning (RL), which defines the long-term evaluation of a policy in a given state. In this paper, we propose Policy-extended Value Function Approximator (PeVFA) which extends the conventional value to be not only a function of state but also an explicit policy representation. Such a...More

Code:

Data:

Your rating :
0

 

Tags
Comments