update samples from Release-52 as a part of SDK release

Author: vizhur

how-to-use-azureml/reinforcement-learning/README.md

@@ -20,11 +20,11 @@ Using these samples, you will be able to do the following.
 
 | File/folder       | Description                                |
 |-------------------|--------------------------------------------|
-| [README.md](README.md)       | This README file.                          |
 | [devenv_setup.ipynb](setup/devenv_setup.ipynb) | Notebook to setup development environment for Azure ML RL |
 | [cartpole_ci.ipynb](cartpole-on-compute-instance/cartpole_ci.ipynb)  | Notebook to train a Cartpole playing agent on an Azure ML Compute Instance |
 | [cartpole_cc.ipynb](cartpole-on-single-compute/cartpole_cc.ipynb)  | Notebook to train a Cartpole playing agent on an Azure ML Compute Cluster (single node) |
 | [pong_rllib.ipynb](atari-on-distributed-compute/pong_rllib.ipynb)   | Notebook to train Pong agent using RLlib on multiple compute targets |
+| [minecraft.ipynb](minecraft-on-distributed-compute/minecraft.ipynb)   | Notebook to train an agent to navigate through a lava maze in the Minecraft game |
 
 ## Prerequisites
 
@@ -111,7 +111,7 @@ contact [[email protected]](mailto:[email protected]) with any additio
 
 For more on SDK concepts, please refer to [notebooks](https://github.com/Azure/MachineLearningNotebooks).
 
-**Please let us know your feedback.**
+**Please let us know your [feedback](https://github.com/Azure/MachineLearningNotebooks/labels/Reinforcement%20Learning).**
 
 
 

how-to-use-azureml/reinforcement-learning/minecraft-on-distributed-compute/docker/cpu/Dockerfile

@@ -0,0 +1,70 @@
+FROM mcr.microsoft.com/azureml/base:openmpi3.1.2-ubuntu18.04
+
+# Install some basic utilities
+RUN apt-get update && apt-get install -y \
+    curl \
+    ca-certificates \
+    sudo \
+	cpio \
+    git \
+    bzip2 \
+    libx11-6 \
+    tmux \
+    htop \
+    gcc \
+    xvfb \
+    python-opengl \
+    x11-xserver-utils \
+    ffmpeg \
+    mesa-utils \
+    nano \
+    vim \
+    rsync \
+ && rm -rf /var/lib/apt/lists/*
+
+# Create a working directory
+RUN mkdir /app
+WORKDIR /app
+
+# Install Minecraft needed libraries
+RUN mkdir -p /usr/share/man/man1 && \
+    sudo apt-get update && \
+    sudo apt-get install -y \
+    openjdk-8-jre-headless=8u162-b12-1 \
+    openjdk-8-jdk-headless=8u162-b12-1 \
+    openjdk-8-jre=8u162-b12-1 \
+    openjdk-8-jdk=8u162-b12-1
+
+# Create a Python 3.7 environment
+RUN conda install conda-build \
+    && conda create -y --name py37 python=3.7.3 \
+    && conda clean -ya
+ENV CONDA_DEFAULT_ENV=py37
+
+# Install minerl
+RUN pip install --upgrade --user minerl
+
+RUN pip install \
+    pandas \
+    matplotlib \
+    numpy \
+    scipy \
+    azureml-defaults \
+    tensorboardX \
+    tensorflow==1.15rc2 \
+    tabulate \
+    dm_tree \
+    lz4 \
+    ray==0.8.3 \
+    ray[rllib]==0.8.3 \
+    ray[tune]==0.8.3
+
+COPY patch_files/* /root/.local/lib/python3.7/site-packages/minerl/env/Malmo/Minecraft/src/main/java/com/microsoft/Malmo/Client/
+
+# Start minerl to pre-fetch minerl files (saves time when starting minerl during training)
+RUN xvfb-run -a -s "-screen 0 1400x900x24" python -c "import gym; import minerl; env = gym.make('MineRLTreechop-v0'); env.close();"
+
+RUN pip install --index-url https://test.pypi.org/simple/ malmo && \
+    python -c "import malmo.minecraftbootstrap; malmo.minecraftbootstrap.download();"
+
+ENV MALMO_XSD_PATH="/app/MalmoPlatform/Schemas"