921kiyo/symbolic-rl
Symbolic Reinforcement Learning using Inductive Logic Programming
This project offers a new approach to teaching an AI agent to navigate and make decisions in an environment. Instead of simply learning from trial and error, it helps the agent understand the underlying rules of how the environment works. You input observed actions and their outcomes, and the system outputs a set of logical rules describing the environment's state transitions, allowing the AI agent to plan actions more efficiently.
No commits in the last 6 months.
Use this if you are a researcher or AI practitioner working on reinforcement learning problems and are looking for methods that improve learning efficiency, enable abstract reasoning, and facilitate knowledge transfer between similar environments.
Not ideal if you need a plug-and-play solution for large-scale, real-world control problems or if you are not comfortable with symbolic AI and logic programming concepts.
Stars
63
Forks
10
Language
Lasso
License
MIT
Category
Last pushed
Feb 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/921kiyo/symbolic-rl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild