antonpuz/DeROL
Deep Reinforcement One-Shot Learning Framework for Artificially Intelligent Classification Systems
This framework helps organizations classify important events when very little training data is available, common in areas like surveillance or patient monitoring. It takes raw event data (like images or network logs) and intelligently decides whether to classify it automatically or assign it to a human analyst, considering resource availability. This is for researchers and developers building intelligent classification systems that need to operate efficiently with limited examples and human support.
No commits in the last 6 months.
Use this if you are developing AI classification systems for scenarios where you have very few examples for new categories and need to manage human analyst resources efficiently.
Not ideal if you have abundant training data for all your classification categories or if you do not need to factor in temporal constraints and human resource allocation.
Stars
36
Forks
11
Language
Python
License
MIT
Category
Last pushed
Apr 30, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/antonpuz/DeROL"
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