turing-usp/Aprendizado-por-Reforco
Repositório de Aprendizado por Reforço desenvolvido pelo Turing USP
Jupyter NotebookMIT
Issues
- 0
- 0
- 0
Explicação On-Policy vs. Off-Policy
#35 opened by nelsonayamashita - 0
Q-Learning
#5 opened by Berbardo - 0
Double DQN
#9 opened by dueiras - 0
Prioritized Experience Replay
#18 opened by fernandokm - 0
Padronizar os gráficos
#33 opened by fernandokm - 0
README DQN
#24 opened by dueiras - 0
Visualização DQN
#25 opened by dueiras - 0
Organizar README.md
#1 opened by Berbardo - 0
- 0
N-Step DQN
#21 opened by Berbardo - 0
Monte Carlo
#3 opened by Berbardo - 0
- 1
Implementações em ambientes mais difíceis
#20 opened by dueiras - 0
Arquivos .py / .ipynb
#19 opened by fernandokm - 6
Convenção de nomenclatura no código
#15 opened by fernandokm - 0
Expected Sarsa
#8 opened by Berbardo - 0
Dyna-Q e Dyna-Q+
#6 opened by Berbardo - 0
- 0
Value Iteration
#2 opened by Berbardo