yardenas/la-mbda
LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization
This project helps researchers and practitioners in robotics and autonomous systems develop more reliable AI. It takes observed data from an environment and uses it to train an AI agent. The output is an optimized control policy that achieves a task while rigorously respecting safety limits, even in uncertain situations. This is ideal for AI researchers, robotics engineers, or anyone designing autonomous systems.
No commits in the last 6 months.
Use this if you need to train an AI agent to perform a task safely, especially when unexpected events or system variations could lead to dangerous outcomes.
Not ideal if your primary goal is rapid, unconstrained task completion without strict safety constraints, or if you are not working with reinforcement learning environments.
Stars
38
Forks
11
Language
Python
License
MIT
Category
Last pushed
Jan 16, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/yardenas/la-mbda"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.