rmst/ddpg

TensorFlow implementation of the DDPG algorithm from the paper Continuous Control with Deep Reinforcement Learning (ICLR 2016)

49
/ 100
Emerging

This project helps machine learning researchers or practitioners develop AI agents that can learn complex motor skills or decision-making processes through trial and error. It takes in descriptions of environments where an agent needs to learn to act, such as simulated robots or game scenarios, and outputs a trained AI policy that can continuously control actions to achieve a goal. It is used by those experimenting with deep reinforcement learning for continuous control tasks.

215 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer looking to experiment with the Deep Deterministic Policy Gradient (DDPG) algorithm for continuous control problems.

Not ideal if you are looking for a maintained, state-of-the-art DDPG implementation with advanced features like batch normalization or prioritized experience replay.

reinforcement-learning robotics-simulation autonomous-control AI-agent-training deep-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

215

Forks

64

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 16, 2018

Commits (30d)

0

Get this data via API

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

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