starting lec6

PeterNg15 · Apr 23, 2023 · ba400fc · ba400fc
1 parent 2ea38ec
commit ba400fc
Show file tree

Hide file tree

Showing 11 changed files with 4,206 additions and 0 deletions.
diff --git a/HW/HW2/HW2_SOLUTIONS.zip b/HW/HW2/HW2_SOLUTIONS.zip
diff --git a/HW/HW2/HW2_soln.ipynb b/HW/HW2/HW2_soln.ipynb
diff --git a/HW/HW2/StudentsPerformance.csv b/HW/HW2/StudentsPerformance.csv
diff --git a/Lecture Notes/Lec6/lec6.aux b/Lecture Notes/Lec6/lec6.aux
@@ -0,0 +1,31 @@
+\relax 
+\providecommand\hyper@newdestlabel[2]{}
+\providecommand\HyperFirstAtBeginDocument{\AtBeginDocument}
+\HyperFirstAtBeginDocument{\ifx\hyper@anchor\@undefined
+\global\let\oldnewlabel\newlabel
+\gdef\newlabel#1#2{\newlabelxx{#1}#2}
+\gdef\newlabelxx#1#2#3#4#5#6{\oldnewlabel{#1}{{#2}{#3}}}
+\AtEndDocument{\ifx\hyper@anchor\@undefined
+\let\newlabel\oldnewlabel
+\fi}
+\fi}
+\global\let\hyper@last\relax 
+\gdef\HyperFirstAtBeginDocument#1{#1}
+\providecommand\HyField@AuxAddToFields[1]{}
+\providecommand\HyField@AuxAddToCoFields[2]{}
+\citation{Bruno}
+\bibcite{DrCoop}{1}
+\@writefile{toc}{\contentsline {section}{\numberline {1}Reinforcement Learning (lecture 14)}{1}{section.1}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {1.1}Abstract Obverview (What is the goal? and when to use it?)}{1}{subsection.1.1}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {1.2}Describing the Agent and Environment Mathematically}{1}{subsection.1.2}\protected@file@percent }
+\bibcite{Stanford}{2}
+\bibcite{ActivationGraphs}{3}
+\bibcite{Bruno}{4}
+\@writefile{toc}{\contentsline {subsubsection}{\numberline {1.2.1}Agent's Goal}{2}{subsubsection.1.2.1}\protected@file@percent }
+\@writefile{toc}{\contentsline {section}{\numberline {2}Actor-Critic (lecture 15)}{2}{section.2}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Dopamine and TD Error}{2}{subsection.2.1}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Value Estimation and TD Error}{2}{subsection.2.2}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Policy Gradients}{2}{subsection.2.3}\protected@file@percent }
+\@writefile{toc}{\contentsline {section}{\numberline {3}Q-Learning (lecture 16)}{2}{section.3}\protected@file@percent }
+\@writefile{toc}{\contentsline {section}{\numberline {4}Q-Estimation (lecture 17)}{2}{section.4}\protected@file@percent }
+\gdef \@abspage@last{2}
diff --git a/Lecture Notes/Lec6/lec6.fdb_latexmk b/Lecture Notes/Lec6/lec6.fdb_latexmk
diff --git a/Lecture Notes/Lec6/lec6.fls b/Lecture Notes/Lec6/lec6.fls