https://github.com/openai/baselines
Tip revision: f05b716b03edb810fb61b2bca0006591c736bdd6 authored by Peter Zhokhov on 14 November 2018, 19:01:05 UTC
trpo - increase reward and eplen buffer to 100 for consistency
trpo - increase reward and eplen buffer to 100 for consistency
Tip revision: f05b716
Dockerfile
FROM python:3.6
RUN apt-get -y update && apt-get -y install ffmpeg
# RUN apt-get -y update && apt-get -y install git wget python-dev python3-dev libopenmpi-dev python-pip zlib1g-dev cmake python-opencv
ENV CODE_DIR /root/code
COPY . $CODE_DIR/baselines
WORKDIR $CODE_DIR/baselines
# Clean up pycache and pyc files
RUN rm -rf __pycache__ && \
find . -name "*.pyc" -delete && \
pip install tensorflow && \
pip install -e .[test]
CMD /bin/bash