cleanrl Docker & Self-Hosted Deployment

GitHub

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

10,578 stars Python Python 57 files · ~105,305 tokens #a2c#actor-critic#advantage-actor-critic#ale#atari#deep-learning#deep-reinforcement-learning#gym
1. Pull Image (DOCKERHUB) docker pull vwxyzjn/cleanrl:latest
2. Docker Run (1-Click Launch) docker run -d --name cleanrl --restart always vwxyzjn/cleanrl:latest
3. Podman Run podman run -d --name cleanrl --restart always vwxyzjn/cleanrl:latest
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/vwxyzjn/cleanrl:latest
5. ORAS Pull (OCI Artifact) oras pull vwxyzjn/cleanrl:latest
Dockerfile 
FROM nvidia/cuda:11.4.2-runtime-ubuntu20.04

# install ubuntu dependencies
ENV DEBIAN_FRONTEND=noninteractive 
RUN apt-get update && \
    apt-get -y install python3-pip xvfb ffmpeg git build-essential python-opengl
RUN ln -s /usr/bin/python3 /usr/bin/python

# install python dependencies
RUN mkdir cleanrl_utils && touch cleanrl_utils/__init__.py
RUN pip install uv --upgrade
COPY pyproject.toml pyproject.toml
COPY uv.lock uv.lock
RUN uv pip install .

COPY entrypoint.sh /usr/local/bin/
RUN chmod 777 /usr/local/bin/entrypoint.sh
ENTRYPOINT ["/usr/local/bin/entrypoint.sh"]

# copy local files
COPY ./cleanrl /cleanrl