rail-berkeley/softlearning

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.

50
/ 100
Established

This is a specialized deep reinforcement learning toolbox for AI/ML researchers and engineers to develop and test 'maximum entropy policies' for autonomous agents in simulated continuous environments. You input environmental data and agent behaviors, and it outputs optimized control policies for tasks like robotic movement or control systems. This is for those who are developing and evaluating advanced AI agents in complex, simulated scenarios.

1,413 stars. No commits in the last 6 months.

Use this if you are a researcher or engineer working on advanced reinforcement learning algorithms for continuous control tasks in simulated environments.

Not ideal if you are a practitioner looking for an off-the-shelf solution to a specific real-world automation problem, or if you prefer PyTorch over TensorFlow.

Reinforcement Learning Research Robotics Simulation Continuous Control AI Autonomous Systems Development Algorithm Prototyping
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

1,413

Forks

250

Language

Python

License

Last pushed

Nov 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rail-berkeley/softlearning"

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