szaguldo-kamaz/FRI-ReinforcementLearning

Fuzzy Rule Interpolation-based Reinforcement Learning

34
/ 100
Emerging

This framework helps researchers and engineers develop reinforcement learning systems where the decision-making rules need to be easily understood by humans. It takes observations from an environment and outputs a set of human-readable fuzzy rules that define how an agent should act, along with the expected 'Q' values for those actions. This is useful for anyone designing autonomous systems who needs transparency in the agent's learned behavior.

No commits in the last 6 months.

Use this if you need to understand or explain why your reinforcement learning agent makes certain decisions, rather than treating it as a 'black box'.

Not ideal if your primary concern is raw performance or if human interpretability of the learned rules is not a priority.

autonomous-systems human-interpretable-AI fuzzy-logic control-systems AI-explainability
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

MATLAB

License

GPL-3.0

Last pushed

Aug 01, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/szaguldo-kamaz/FRI-ReinforcementLearning"

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