An AI-powered entry in TopGit's GitHub warehouse: DLR-RM/rl-baselines3-zoo, 2.9k stars, AI Tools, Python. A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
Snapshot summary built from the project's own GitHub metadata — there's no written TopGit review yet. The page will update automatically when a full review is published.
WHY NO REVIEW YET
TopGit writes full reviews for the most-starred, most-requested repositories. This page is a snapshot until then — see the READ ME tab for the original README in full.
RL Baselines3 Zoo: A Training Framework for Stable Baselines3 Reinforcement Learning Agents
RL Baselines3 Zoo is a training framework for Reinforcement Learning (RL), using Stable Baselines3.
It provides scripts for training, evaluating agents, tuning hyperparameters, plotting results and recording videos.
In addition, it includes a collection of tuned hyperparameters for common environments and RL algorithms, and agents trained with those settings.
We are looking for contributors to complete the collection!
Goals of this repository:
Provide a simple interface to train and enjoy RL agents
Benchmark the different Reinforcement Learning algorithms
Provide tuned hyperparameters for each environment and RL algorithm
Have fun with the trained agents!
This is the SB3 version of the original SB2 rl-zoo.
Documentation
Documentation is available online: https://rl-baselines3-zoo.readthedocs.io/
Installation
Minimal installation
From source:
pip install -e .
As a python package:
pip install rl_zoo3
Note: you can do python -m rl_zoo3.train from any folder and you have access to rl_zoo3 command line interface, for instance, rl_zoo3 train is equivalent to python train.py
Full installation (with extra envs and test dependencies)
The RL Zoo has some integration with other libraries/services like Weights & Biases for experiment tracking or Hugging Face for storing/sharing trained models. You can find out more in the dedicated section of the documentation.
Plot Scripts
Please see the dedicated section of the documentation.
Enjoy a Trained Agent
Note: to download the repo with the trained agents, you must use git clone --recursive https://github.com/DLR-RM/rl-baselines3-zoo in order to clone the submodule too.
If the trained agent exists, then you can see it in action using:
python enjoy.py --algo algo_name --env env_id
For example, enjoy A2C on Breakout during 5000 timesteps:
Please see the dedicated section of the documentation.
Custom Configuration
Please see the dedicated section of the documentation.
Current Collection: 200+ Trained Agents!
Final performance of the trained agents can be found in benchmark.md. To compute them, simply run python -m rl_zoo3.benchmark.
List and videos of trained agents can be found on our Huggingface page: https://huggingface.co/sb3
NOTE: this is not a quantitative benchmark as it corresponds to only one run (cf issue #38). This benchmark is meant to check algorithm (maximal) performance, find potential bugs and also allow users to have access to pretrained agents.
Atari Games
7 atari games from OpenAI benchmark (NoFrameskip-v4 versions).
RL Algo
BeamRider
Breakout
Enduro
Pong
Qbert
Seaquest
SpaceInvaders
A2C
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
PPO
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
DQN
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
QR-DQN
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
Additional Atari Games (to be completed):
RL Algo
MsPacman
Asteroids
RoadRunner
A2C
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
PPO
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
DQN
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
QR-DQN
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
Classic Control Environments
RL Algo
CartPole-v1
MountainCar-v0
Acrobot-v1
Pendulum-v1
MountainCarContinuous-v0
ARS
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
A2C
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
PPO
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
DQN
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
N/A
N/A
QR-DQN
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
N/A
N/A
DDPG
N/A
N/A
N/A
:heavy_check_mark:
:heavy_check_mark:
SAC
N/A
N/A
N/A
:heavy_check_mark:
:heavy_check_mark:
TD3
N/A
N/A
N/A
:heavy_check_mark:
:heavy_check_mark:
TQC
N/A
N/A
N/A
:heavy_check_mark:
:heavy_check_mark:
TRPO
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
Box2D Environments
RL Algo
BipedalWalker-v3
LunarLander-v2
LunarLanderContinuous-v2
BipedalWalkerHardcore-v3
CarRacing-v0
ARS
:heavy_check_mark:
:heavy_check_mark:
A2C
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
PPO
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
DQN
N/A
:heavy_check_mark:
N/A
N/A
N/A
QR-DQN
N/A
:heavy_check_mark:
N/A
N/A
N/A
DDPG
:heavy_check_mark:
N/A
:heavy_check_mark:
SAC
:heavy_check_mark:
N/A
:heavy_check_mark:
:heavy_check_mark:
TD3
:heavy_check_mark:
N/A
:heavy_check_mark:
:heavy_check_mark:
TQC
:heavy_check_mark:
N/A
:heavy_check_mark:
:heavy_check_mark:
TRPO
:heavy_check_mark:
:heavy_check_mark:
PyBullet Environments
See https://github.com/bulletphysics/bullet3/tree/master/examples/pybullet/gym/pybullet_envs.
Similar to MuJoCo Envs but with a free (MuJoCo 2.1.0+ is now free!) easy to install simulator: pybullet. We are using BulletEnv-v0 version.
Note: those environments are derived from Roboschool and are harder than the Mujoco version (see Pybullet issue)
RL Algo
Walker2D
HalfCheetah
Ant
Reacher
Hopper
Humanoid
ARS
A2C
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
PPO
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
DDPG
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
SAC
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
TD3
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
TQC
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
TRPO
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
PyBullet Envs (Continued)
RL Algo
Minitaur
MinitaurDuck
InvertedDoublePendulum
InvertedPendulumSwingup
A2C
PPO
DDPG
SAC
TD3
TQC
MuJoCo Environments
RL Algo
Walker2d
HalfCheetah
Ant
Swimmer
Hopper
Humanoid
ARS
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
A2C
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
PPO
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
DDPG
SAC
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
TD3
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
TQC
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
TRPO
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
Robotics Environments
See https://gym.openai.com/envs/#robotics and https://github.com/DLR-RM/rl-baselines3-zoo/pull/71
MuJoCo version: 1.50.1.0
Gym version: 0.18.0
We used the v1 environments.
RL Algo
FetchReach
FetchPickAndPlace
FetchPush
FetchSlide
HER+TQC
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
Panda robot Environments
See https://github.com/qgallouedec/panda-gym/.
Similar to MuJoCo Robotics Envs but with a free easy to install simulator: pybullet.
We used the v1 environments.
RL Algo
PandaReach
PandaPickAndPlace
PandaPush
PandaSlide
PandaStack
HER+TQC
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
MiniGrid Envs
See https://github.com/Farama-Foundation/Minigrid.
A simple, lightweight and fast Gym environments implementation of the famous gridworld.
RL Algo
Empty-Random-5x5
FourRooms
DoorKey-5x5
MultiRoom-N4-S5
Fetch-5x5-N2
GoToDoor-5x5
PutNear-6x6-N2
RedBlueDoors-6x6
LockedRoom
KeyCorridorS3R1
Unlock
ObstructedMaze-2Dlh
A2C
PPO
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
:heavy_check_mark:
DQN
QR-DQN
TRPO
There are 22 environment groups (variations for each) in total.
Colab Notebook: Try it Online!
You can train agents online using Colab notebook.
Passing arguments in an interactive session
The zoo is not meant to be executed from an interactive session (e.g: Jupyter Notebooks, IPython), however, it can be done by modifying sys.argv and adding the desired arguments.
Yes — DLR-RM/rl-baselines3-zoo ships under the MIT license, which makes its source code freely readable (and, depending on license terms, forkable and reusable). Source: github.com/DLR-RM/rl-baselines3-zoo.
What else is in the AI Tools space?
DLR-RM/rl-baselines3-zoo is tracked by TopGit under the AI Tools category, alongside 17 GitHub-tagged topics. Trending and Topics pages list peer repositories of comparable stars and language.
What is DLR-RM/rl-baselines3-zoo?
DLR-RM/rl-baselines3-zoo (DLR-RM/rl-baselines3-zoo) is a Python project on GitHub. From the project's own README: A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
What license does DLR-RM/rl-baselines3-zoo use?
DLR-RM/rl-baselines3-zoo is released under the MIT license. Always verify the LICENSE file directly on GitHub for the authoritative terms — license strings can be edited out of sync with a project's actual stance.
Where can I see DLR-RM/rl-baselines3-zoo in action?
The project maintains a homepage at https://rl-baselines3-zoo.readthedocs.io. The README tab on this page also usually contains screenshots and a quickstart.
Where do I read more about DLR-RM/rl-baselines3-zoo?
This TopGit page is a snapshot — the READ ME tab shows the project's own README content (links stripped, images preserved). The GitHub repository at github.com/DLR-RM/rl-baselines3-zoo is the definitive source.
Why is DLR-RM/rl-baselines3-zoo categorized under AI Tools?
TopGit places DLR-RM/rl-baselines3-zoo in the AI Tools category based on its GitHub topics and description (tagged: "deep-reinforcement-learning", "gym", "hyperparameter-optimization"). Categories are assigned from real repository metadata, not editorial guesswork.
Read full README in the tab above.
Want a second opinion on rl-baselines3-zoo?
Ask an AI that can read this page — one click and you get its take on rl-baselines3-zoo.