文件名称：Reinforcement-Learning-David-Silver-Solution
文件大小：919KB
文件格式：ZIP
更新时间：2024-05-18 15:26:37
Python
Easy21中的蒙特卡洛控制 Easy21中的TD学习 Easy21中的线性函数逼近
【文件预览】：
Reinforcement-Learning-David-Silver-Solution-master
----plot.py(1KB)
----env.py(2KB)
----results()
--------training_loss_with_Function_Approximation.png(25KB)
--------MSE_loss_of_TD_learning.png(18KB)
--------MSE_loss_with_Function_Approximation.png(22KB)
--------Q_value_of_TD_learning_lambda=1.png(132KB)
--------Qstar.png(122KB)
--------Q_value_of_TD_learning_lambda=0.png(124KB)
--------Q_value_with_Function_Approximation_lambda=0.png(127KB)
--------training_loss_of_TD_learning.png(17KB)
--------Q_value_with_Function_Approximation_lambda=1.png(127KB)
----MC_Control.py(3KB)
----Function_Approximation.py(5KB)
----README.md(1KB)
----__pycache__()
--------plot.cpython-35.pyc(2KB)
--------env.cpython-35.pyc(2KB)
--------MC_Control.cpython-35.pyc(2KB)
--------policy.cpython-35.pyc(948B)
----TD_Learning.py(3KB)
----Easy21-Johannes.pdf(226KB)
----policy.py(725B)