Causally Correct Partial Models for Reinforcement Learning

Papamakarios George
Papamakarios George
Ke Nan Rosemary
Ke Nan Rosemary
Jiang Ray
Jiang Ray
Merzic Hamza
Merzic Hamza
Wang Jane
Wang Jane
Mitrovic Jovana
Mitrovic Jovana
Besse Frederic
Besse Frederic
Cited by: 2|Bibtex|Views51
Other Links: arxiv.org

Abstract:

In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions. However, jointly modeling future observations can be computationally expensive or even intractable if the observations are high-dimensional (e.g. images). For this reason, previous works have considered partia...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments