enlite-ai/maze

Maze Applied Reinforcement Learning Framework

49
/ 100
Emerging

Provides PyTorch-based Perception Modules for composing neural network architectures (dense, convolutional, graph, attention, recurrent) with built-in observation preprocessing and masking. Supports multi-step and multi-agent environments beyond standard Gym compatibility, alongside trainers for A2C, PPO, Impala, SAC, and Evolution Strategies with dictionary action/observation spaces. Configuration managed through Hydra, enabling imitation learning and policy fine-tuning workflows for complex industrial decision problems.

286 stars.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

286

Forks

12

Language

Python

License

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/enlite-ai/maze"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.