Sökning: "Rein-forcement Learning"

Hittade 2 uppsatser innehållade orden Rein-forcement Learning.

1. 1. Deep Reinforcement Learning in Cart Pole and Pong

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Dennis Kuurne Uussilta; Viktor Olsson; [2020]
   Nyckelord :Artificial Intelligence; Machine Learning; Rein-forcement Learning; Deep Q-learning Network; CartPole; Pong;

   Sammanfattning : In this project, we aim to reproduce previous resultsachieved with Deep Reinforcement Learning. We present theMarkov Decision Process model as well as the algorithms Q-learning and Deep Q-learning Network (DQN). We implement aDQN agent, first in an environment called CartPole, and later inthe game Pong. LÄS MER

3. 2. Robust Reinforcement Learning in Continuous Action/State Space

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Axel Grönland; Viktor Eriksson Möllerstedt; [2020]
   Nyckelord :Robust Reinforcement Learning; Neural Net-work; Dynamical Systems; TD Learning;

   Sammanfattning : In this project we aim to apply Robust Reinforce-ment Learning algorithms, presented by Doya and Morimoto [1],[2], to control problems. Specifically, we train an agent to balancea pendulum in the unstable equilibrium, which is the invertedstate.We investigate the performance of controllers based on twodifferent function approximators. LÄS MER