icaros-usc/dqd-rl

Official implementation of "Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning"

22
/ 100
Experimental

This project helps researchers create a wide variety of effective agent behaviors for complex environments. It takes simulated robot locomotion tasks as input and outputs diverse sets of policies, or strategies, that solve those tasks with different approaches. This is for researchers in artificial intelligence and robotics who are developing robust and versatile autonomous agents.

No commits in the last 6 months.

Use this if you need to generate a diverse collection of high-performing agent policies, rather than just one optimal policy, for simulated control tasks.

Not ideal if your primary goal is to find a single, globally optimal solution without concern for the diversity of behaviors.

robotics research agent behavior generation reinforcement learning locomotion tasks quality diversity
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

22

Forks

Language

Python

License

MIT

Last pushed

Oct 03, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/icaros-usc/dqd-rl"

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