Applied Reinforcement Learning with Python
MazeRL is an application oriented Deep Reinforcement Learning (RL) framework, addressing real-world decision problems. Our vision is to cover the complete development life cycle of RL applications ranging from simulation engineering up to agent development, training and deployment.
This is a preliminary, non-stable release of Maze. It is not yet complete and not all of our interfaces have settled yet. Hence, there might be some breaking changes on our way towards the first stable release.
Below we list a few selected Maze features.
- Design and visualize your policy and value networks with the
It is based on PyTorch and provides a large variety of neural network building blocks and model styles.
Quickly compose powerful representation learners from building blocks such as: dense,
convolution, graph convolution and attention, recurrent architectures, action- and observation masking,
- Create the conditions for efficient RL training without writing boiler plate code, e.g. by supporting
best practices like pre-processing and
normalizing your observations.
- Maze supports advanced environment structures reflecting
the requirements of real-world industrial decision problems such as multi-step and multi-agent scenarios.
You can of course work with existing Gym-compatible environments.
- Use the provided Maze trainers (A2C, PPO, Impala, SAC, Evolution Strategies),
which are supporting dictionary action and observation spaces as well as multi-step (auto-regressive policies) training.
Or stick to your favorite tools and trainers by combining Maze with other RL frameworks.
- Out of the box support for advanced training workflows such as imitation learning from teacher policies and
- Keep even complex application and experiment configuration manageable with the Hydra Config System.
You can try Maze without prior installation! We provide a series of Getting started notebooks to help you get familiar with Maze. These notebooks can be viewed and executed in Google Colab - just pick any of the included notebooks and click on the
If you want to install Maze locally, make sure PyTorch is installed and then get the latest released version of Maze as follows:
pip install -U maze-rl # optionally install RLLib if you want to use it in combination with Maze pip install ray[rllib] tensorflow
Read more about other options like the installation of the latest
:zap: We encourage you to start with Python 3.7, as many popular environments like Atari or Box2D can not easily
be installed in newer Python environments. Maze itself supports newer Python versions, but for Python 3.9 you might have to
install additional binary dependencies manually
Alternatively you can work with Maze in a container with pre-installed Jupyter lab: Run
docker run -p 8888:8888 enliteai/maze:playgroundand open
localhost:8888in your browser. This loads Jupyter
To see Maze in action, check out a first example.
Training and deploying your agent is as simple as can be:
from maze.api.run_context import RunContext from maze.core.wrappers.maze_gym_env_wrapper import GymMazeEnv rc = RunContext(env=lambda: GymMazeEnv('CartPole-v0'), algorithm="ppo") rc.train(n_epochs=50) # Run trained policy. env = GymMazeEnv('CartPole-v0') obs = env.reset() done = False while not done: action = rc.compute_action(obs) obs, reward, done, info = env.step(action)
Step by Step Tutorial
- Clone this project template repo to start your own Maze project.