Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Maze Applied Reinforcement Learning Framework
| Date | Stars |
|---|---|
| 2026-07-25 | 293 |
| 2026-07-28 | 293 |
| 2026-07-30 | 293 |
| 2026-07-31 | 292 |
| 2026-08-06 | 292 |
Today
— stars today
This week
-1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
[](https://github.com/enlite-ai/maze/actions/workflows/codeql-analysis.yml)
[](https://github.com/enlite-ai/maze/actions/workflows/github-ci.yml)
[](https://github.com/enlite-ai/maze/issues)
# 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.*
## Spotlight Features
Below we list a few selected Maze features.
- Design and visualize your policy and value networks with the
[Perception Module](https://maze-rl.readthedocs.io/en/latest/policy_and_value_networks/perception_overview.html).
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,
self-attention etc.
- Create the conditions for efficient RL training without writing boiler plate code, e.g. by supporting
best practices like [pre-processing](https://maze-rl.readthedocs.io/en/latest/environment_customization/observation_pre_processing.html) and
[normalizing](https://maze-rl.readthedocs.io/en/latest/environment_customization/observation_normalization.html) your observations.
- Maze supports advanced [environment structures](https://maze-rl.readthedocs.io/en/latest/concepts_and_structure/env_hierarchy.html) 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](https://maze-rl.readthedocs.io/en/latest/best_practices_and_tutorials/integrating_gym_environment.html).
- Use the provided [Maze trainers](https://maze-rl.readthedocs.io/en/latest/trainers/maze_trainers.html) (A2C, PPO, Impala, SAC, Evolution Strategies),
which are supporting dictionary action and observation spaces as well as multi-step (auto-regressive policies) training.
- Out of the box support for advanced training workflows such as [imitation learning from teacher policies and
policy fine-tuning](https://maze-rl.readthedocs.io/en/latest/workflow/imitation_and_fine_tuning.html).
- Keep even complex application and experiment configuration manageable with the [Hydra Config System](https://maze-rl.readthedocs.io/en/latest/concepts_and_structure/hydra.html).
## Get Started
* Make sure [PyTorch](https://pytorch.org/get-started/locally/) is installed and then get the latest released version of Maze as follows:
pip install -U maze-rl
[Read more about other options](https://maze-rl.readthedocs.io/en/latest/getting_started/installation.html) like the installation of the latest
development version.
:zap: Maze is compatible with Python 3.9 to 3.10. We encourage you to start with **Python 3.10**.
If you intend to use popular environments like Atari or Box2D you might need to [install additional binary dependencies manually](Excerpt of 9,000 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:42c7aaeff47c2941, topic:reinforcement-learning, desc:reinforcement learning, readme:reinforcement learning
matched fp:42c7aaeff47c2941, topic:monitoring
matched fp:42c7aaeff47c2941, topic:deep-learning
matched fp:42c7aaeff47c2941, topic:automation