denisyarats/proto

Proto-RL: Reinforcement Learning with Prototypical Representations

41
/ 100
Emerging

This project helps machine learning researchers develop intelligent agents that learn new tasks more efficiently. It takes raw environmental data from simulations or real-world scenarios and outputs a trained agent capable of performing a specific task. Reinforcement learning researchers and practitioners who want to build agents that generalize well to new environments would use this.

No commits in the last 6 months.

Use this if you are a reinforcement learning researcher looking to pre-train agents on various tasks to improve their learning speed and adaptability.

Not ideal if you are looking for a ready-to-use, pre-trained agent for a specific real-world application without delving into agent training methodologies.

reinforcement-learning intelligent-agents machine-learning-research robotics-learning agent-pretraining
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

86

Forks

13

Language

Python

License

MIT

Last pushed

Jun 12, 2022

Commits (30d)

0

Get this data via API

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

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