IBM/LOA

Neuro-Symbolic Reinforcement Learning: Logical Optimal Action (LOA), a novel RL with Logical Neural Network (LNN) on text-based games

45
/ 100
Emerging

This project helps researchers in AI and natural language processing develop agents that can understand and interact with text-based environments more effectively. It takes descriptions of a game world and potential actions, then outputs logical rules that guide an agent's decisions. AI researchers working on improving reinforcement learning for language-based tasks would use this.

No commits in the last 6 months.

Use this if you are an AI researcher experimenting with neuro-symbolic methods to create more interpretable and generalizable reinforcement learning agents for text-based games.

Not ideal if you are looking for a ready-to-use game AI for a specific commercial game, or if you need a solution for non-textual environments.

AI research natural language processing reinforcement learning text-based games neuro-symbolic AI
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

56

Forks

19

Language

Python

License

MIT

Last pushed

Sep 17, 2025

Commits (30d)

0

Get this data via API

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

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