Skip to content


Switch branches/tags

Latest commit


Git stats


Failed to load latest commit information.
Latest commit message
Commit time


This repository contains an implementation of distributed reinforcement learning agent where both training and inference are performed on the learner.


Four agents are implemented:

The code is already interfaced with the following environments:

However, any reinforcement learning environment using the gym API can be used.

For a detailed description of the architecture please read our paper. Please cite the paper if you use the code from this repository in your work.


    title={SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference},
    author={Lasse Espeholt and Rapha{\"e}l Marinier and Piotr Stanczyk and Ke Wang and Marcin Michalski},

Pull Requests

At this time, we do not accept pull requests. We are happy to link to forks that add interesting functionality.


There are a few steps you need to take before playing with SEED. Instructions below assume you run the Ubuntu distribution.

apt-get install git
  • Clone SEED git repository:
git clone
cd seed_rl

Local Machine Training on a Single Level

To easily start with SEED we provide a way of running it on a local machine. You just need to run one of the following commands (adjusting number of actors and number of envs. per actor/env. batch size to your machine):

./ [Game] [Agent] [number of actors] [number of envs. per actor]
./ atari r2d2 4 4
./ football vtrace 4 1
./ dmlab vtrace 4 4
./ mujoco ppo 4 32 --gin_config=/seed_rl/mujoco/gin/ppo.gin

It will build a Docker image using SEED source code and start the training inside the Docker image. Note that hyper parameters are not tuned in the runs above. Tensorboard is started as part of the training. It can be viewed under http://localhost:6006 by default.

We also provide a sample script for running training with tuned parameters for HalfCheetah-v2. This setup runs training with 8x32=256 parallel environments to make training faster. The sample complexity can be improved at the cost of slower training by running fewer environments and increasing the unroll_length parameter.


Distributed Training using AI Platform

Note that training with AI Platform results in charges for using compute resources.

The first step is to configure GCP and a Cloud project you will use for training:

gcloud auth login
gcloud config set project [YOUR_PROJECT]

Then you just need to execute one of the provided scenarios:


This will build the Docker image, push it to the repository which AI Platform can access and start the training process on the Cloud. Follow output of the command for progress. You can also view the running training jobs at

DeepMind Lab Level Cache

By default majority of DeepMind Lab's CPU usage is generated by creating new scenarios. This cost can be eliminated by enabling level cache. To enable it, set the level_cache_dir flag in the dmlab/ As there are many unique episodes it is a good idea to share the same cache across multiple experiments. For AI Platform you can add --level_cache_dir=gs://${BUCKET_NAME}/dmlab_cache to the list of parameters passed in gcp/ to the experiment.

Baseline data on ATARI-57

We provide baseline training data for SEED's R2D2 trained on ATARI games in the form of training curves (checkpoints and Tensorboard event files coming soon). We provide data for 4 independent seeds run up to 40e9 environment frames.

The hyperparameters and evaluation procedure are the same as in section A.3.1 in the paper.

Training curves

Training curves are available on this page.

Checkpoints and Tensorboard event files

Checkpoints and tensorboard event files can be downloaded individually here or as a single (70GBs) zip file.

Additional links

SEED was used as a core infrastructure piece for the What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study paper. A colab that reproduces plots from the paper can be found here.


SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.








No releases published


No packages published