[AMR] Many learnings from exercises

electives/amr/parts/05_planning-control/01_motion-planning-exploration/01_a-star-algorithm.tex

@@ -3,6 +3,7 @@ Function \texttt{h(\dots)} is a lower bound of optimal cost.
 % TODO: If space constrained, move to below
 % Init vert. with \texttt{dist}, \texttt{totDistEst} to $\8$, \texttt{prev} \texttt{undef}, \texttt{start}
 \begin{algorithm}
+    \small
     \begin{algorithmic}[1]
         \Procedure{Astar}{\texttt{Graph, start, goal}}
             \For{each \texttt{v} in \texttt{Graph.Verticies}}

electives/amr/parts/05_planning-control/01_motion-planning-exploration/02_rrt.tex

@@ -1,5 +1,7 @@
+\newpage
 \subsubsection{Rapidly-Exploring Random Tree (RRT)}
 \begin{algorithm}
+    \small
     \begin{algorithmic}[1]
         \Procedure{RRT}{\texttt{start, goal}}
             \State \Call{insertVertex}{\texttt{start, Graph}}
@@ -28,6 +30,7 @@
 Returns a collision-free path as graph. Need nearest neighbour search.
 Extension to RRT* to make path better:
 \begin{algorithm}
+    \small
     \begin{algorithmic}[1]
         \State $X_{\text{near}} \gets$ \Call{neighbours}{Graph, $x_f$, $R$}
         \State $x_{\min} \gets$ \Call{neighbours}{Graph, $x_f$, $R$}

electives/amr/parts/05_planning-control/02_learning-to-act/02_reinforcement-learning.tex

@@ -21,7 +21,7 @@ Then update: $Q_{i + 1}(\vec{x}, \vec{u}) = (1 - \alpha)Q_i(\vec{x}, \vec{u}) +
 Called off-policy learning, needs exploration. Simplest is random actions ($\varepsilon$-greedy):
 $\varepsilon$ is prob. to act randomly, $1 - \varepsilon$ is prob. to act on pol. {\color{red} Space explored, still doing random stuff}
 
-\bi{Approaches} 
+\bi{DL-Approaches}
 \textit{Model-based} (estimate trans. model, e.g. Dyna),
 Value-based (estimate val or $Q$-func and extract pol., e.g. Q-Learn),
 Actor-Critic (estim. val or $Q$ of curr. pol., improve pol., e.g. A3C, SAC),