Speeding up Reinforcement Learning with Learned Models
Author:
Pou Mulet, Bartomeu
Other authors:
Universitat Politècnica de Catalunya. Departament de Ciències de la Computació; Martín Muñoz, Mario
Abstract:
In this master thesis, we have tried to solve two of most prominent Reinforcement Learning problems: sparse rewards and sample efficiency. The combination of Model Based Reinforcement Learning, Hindsight Experience Replay and off-policy methods is the approach we took to solve the problems.
Subject(s):
-Àrees temàtiques de la UPC::Informàtica -Reinforcement learning -Algorithms -Model Based Reinforcement Learning -Hindsight Experience Replay -off-policy methods -sparse rewards -sample efficiency. -Aprenentatge per reforç -Algorismes
