Browse Source

Remove leftover starred floats

arxiv-v3
Markus Kaiser 8 months ago
parent
commit
f362d0a49f
1 changed files with 5 additions and 5 deletions
  1. +5
    -5
      dynamic_dirichlet_deep_gp.tex

+ 5
- 5
dynamic_dirichlet_deep_gp.tex View File

@@ -397,7 +397,7 @@ We use an implementation of DAGP in TensorFlow~\parencite{tensorflow2015-whitepa
\subsection{Noise Separation}
\label{subsec:choicenet}
%
\begin{figure*}[t]
\begin{figure}[t]
\centering
\captionof{table}{
\label{tab:choicenet}
@@ -453,7 +453,7 @@ We use an implementation of DAGP in TensorFlow~\parencite{tensorflow2015-whitepa
The bimodal DAGP identifies the signal perfectly up to 40\,\% outliers.
For 60\,\% outliers, some of the noise is interpreted as signal, but the latent function is still recovered.
}
\end{figure*}
\end{figure}
%
We begin with an experiment based on a noise separation problem.
We apply DAGP to a one-dimensional regression problem with uniformly distributed asymmetric outliers in the training data.
@@ -481,7 +481,7 @@ While the function has still been identified well, some of the noise is also exp
\subsection{Multimodal Data}
\label{subsec:semi_bimodal}
%
\begin{figure*}[t]
\begin{figure}[t]
\centering
\includestandalone{figures/semi_bimodal_joint}
\includestandalone{figures/semi_bimodal_attrib}
@@ -517,7 +517,7 @@ At $x = -10$ the inferred modes and assignment processes start reverting to thei

\subsection{Mixed Cart-Pole Systems}
\label{subsec:cartpole}
\begin{table*}[t]
\begin{table}[t]
\centering
\caption{
\label{tab:cartpole}
@@ -553,7 +553,7 @@ At $x = -10$ the inferred modes and assignment processes start reverting to thei
10 & GPR Short & {\textemdash} & {\textemdash} & -5.24 \pm 0.04 & -5.14 \pm 0.04 & \bfseries 0.903 \pm 0.003 & \bfseries 0.792 \pm 0.003 \\
\bottomrule
\end{tabular}
\end{table*}
\end{table}
Our third experiment is based on the cart-pole benchmark for reinforcement learning as described by~\textcite{barto_neuronlike_1983} and implemented in OpenAI Gym~\parencite{brockman_openai_2016}.
In this benchmark, the objective is to apply forces to a cart moving on a frictionless track to keep a pole, which is attached to the cart via a joint, in an upright position.
We consider the regression problem of predicting the change of the pole's angle given the current state of the cart and the action applied.

Loading…
Cancel
Save