Towards a Simple Approach to Multi-step Model-based Reinforcement Learning

Kavosh Asadi
Kavosh Asadi
Evan Cater
Evan Cater

arXiv: Learning, Volume abs/1811.00128, 2018.

Cited by: 0|Views28
EI

Abstract:

When environmental interaction is expensive, model-based reinforcement learning offers a solution by planning ahead and avoiding costly mistakes. Model-based agents typically learn a single-step transition model. In this paper, we propose a multi-step model that predicts the outcome of an action sequence with variable length. We show that...More

Code:

Data:

Get fulltext within 24h
Bibtex
Your rating :
0

 

Tags
Comments