Release 0.9

Main changes are detailed below:

New features -
* CARLA 0.7 simulator integration
* Human control of the game play
* Recording of human game play and storing / loading the replay buffer
* Behavioral cloning agent and presets
* Golden tests for several presets
* Selecting between deep / shallow image embedders
* Rendering through pygame (with some boost in performance)

API changes -
* Improved environment wrapper API
* Added an evaluate flag to allow convenient evaluation of existing checkpoints
* Improve frameskip definition in Gym

Bug fixes -
* Fixed loading of checkpoints for agents with more than one network
* Fixed the N Step Q learning agent python3 compatibility

install.sh

@@ -192,10 +192,14 @@ if [ ${INSTALL_NEON} -eq 1 ]; then
 
     # Neon
     sudo -E apt-get install libhdf5-dev libyaml-dev pkg-config clang virtualenv libcurl4-openssl-dev libopencv-dev libsox-dev -y
-    git clone https://github.com/NervanaSystems/neon.git
-    cd neon && make sysinstall -j
-    cd ..
+    pip3 install nervananeon
+fi
+
+if ! [ -x "$(command -v nvidia-smi)" ]; then
+    # Intel Optimized TensorFlow
+    pip3 install https://anaconda.org/intel/tensorflow/1.3.0/download/tensorflow-1.3.0-cp35-cp35m-linux_x86_64.whl
+else
+    # GPU supported TensorFlow
+    pip3 install tensorflow-gpu
 fi
 
-# Intel Optimized TensorFlow
-pip3 install https://anaconda.org/intel/tensorflow/1.3.0/download/tensorflow-1.3.0-cp35-cp35m-linux_x86_64.whl