Commit f2d8e10f authored by Matthew Hausknecht's avatar Matthew Hausknecht Committed by GitHub

Merge pull request #61 from DurgeshSamant/stamina

Stamina
parents 167bca8b b2b47f11
...@@ -15,7 +15,7 @@ install: ...@@ -15,7 +15,7 @@ install:
brew install cartr/qt4/qt brew install cartr/qt4/qt
; ;
fi fi
- sudo -H pip install --upgrade nose numpy - sudo -H pip2 install --upgrade nose numpy
os: os:
- linux - linux
- osx - osx
...@@ -27,4 +27,4 @@ env: ...@@ -27,4 +27,4 @@ env:
script: script:
- mkdir build && cd build - mkdir build && cd build
- cmake -DCMAKE_BUILD_TYPE=RelwithDebInfo .. && make -j4 && make install - cmake -DCMAKE_BUILD_TYPE=RelwithDebInfo .. && make -j4 && make install
- cd .. && pip install --user . && nosetests --exe -vd tests/test_basic.py - cd .. && pip2 install --user . && nosetests --exe -vd tests/test_basic.py
...@@ -286,7 +286,7 @@ follows: ...@@ -286,7 +286,7 @@ follows:
\subsubsection{High Level State Feature List} \subsubsection{High Level State Feature List}
Let $T$ denote the number of teammates in the HFO game and $O$ the Let $T$ denote the number of teammates in the HFO game and $O$ the
number of opponents. There are a total of $10 + 6T + 3O$ high-level number of opponents. There are a total of $10 + 6T + 3O + 2$ high-level
features. features.
\begin{enumerate}[noitemsep] \begin{enumerate}[noitemsep]
...@@ -328,6 +328,7 @@ features. ...@@ -328,6 +328,7 @@ features.
the last action taken was successful, either in accomplishing the the last action taken was successful, either in accomplishing the
usual intent of the action or (primarily for the offense) in some other way such as usual intent of the action or (primarily for the offense) in some other way such as
getting out of a goal-collision state. 1 for yes, -1 for no.} getting out of a goal-collision state. 1 for yes, -1 for no.}
\item [$+1$] {\textbf{Stamina} Agent's Stamina: Low stamina slows movement.}
\end{enumerate} \end{enumerate}
\begin{figure}[htp] \begin{figure}[htp]
...@@ -468,7 +469,7 @@ the above categories. These features are referred to as \textit{other ...@@ -468,7 +469,7 @@ the above categories. These features are referred to as \textit{other
\subsubsection{Low Level State Feature List} \subsubsection{Low Level State Feature List}
Let $T$ denote the number of teammates and $O$ denote the number of Let $T$ denote the number of teammates and $O$ denote the number of
opponents in the HFO game. Then there are a total of $58 + 9T + 9O$ opponents in the HFO game. Then there are a total of $58 + 9T + 9O + 1$
low-level features: low-level features:
\begin{enumerate}[noitemsep] \begin{enumerate}[noitemsep]
......
...@@ -16,7 +16,7 @@ HighLevelFeatureExtractor::HighLevelFeatureExtractor(int num_teammates, ...@@ -16,7 +16,7 @@ HighLevelFeatureExtractor::HighLevelFeatureExtractor(int num_teammates,
assert(numOpponents >= 0); assert(numOpponents >= 0);
numFeatures = num_basic_features + features_per_teammate * numTeammates numFeatures = num_basic_features + features_per_teammate * numTeammates
+ features_per_opponent * numOpponents; + features_per_opponent * numOpponents;
numFeatures++; // action status numFeatures+=2; // action status, stamina
feature_vec.resize(numFeatures); feature_vec.resize(numFeatures);
} }
...@@ -185,6 +185,7 @@ HighLevelFeatureExtractor::ExtractFeatures(const rcsc::WorldModel& wm, ...@@ -185,6 +185,7 @@ HighLevelFeatureExtractor::ExtractFeatures(const rcsc::WorldModel& wm,
} else { } else {
addFeature(FEAT_MIN); addFeature(FEAT_MIN);
} }
addNormFeature(self.stamina(), 0., observedStaminaMax);
assert(featIndx == numFeatures); assert(featIndx == numFeatures);
// checkFeatures(); // checkFeatures();
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment