tayalmanan28/Safe_Reinforcement_Learning

Repository containing the code for safe reinforcement learning in two custom environments

41
/ 100
Emerging

This project helps robotics engineers or control system designers develop reinforcement learning agents that can safely navigate complex environments. It takes an existing reinforcement learning agent's proposed actions and minimally adjusts them to prevent the system from entering unsafe states. The output is a safer set of actions that still guide the robot towards its goal, preventing damage or hazardous operation.

No commits in the last 6 months.

Use this if you are designing control systems for robots or autonomous agents and need to ensure they operate safely, avoiding collisions or forbidden areas while learning.

Not ideal if you are looking for a general-purpose reinforcement learning library without a specific focus on safety-critical applications.

robotics control-systems autonomous-navigation agent-safety path-planning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

46

Forks

9

Language

Python

License

MIT

Last pushed

Apr 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tayalmanan28/Safe_Reinforcement_Learning"

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