Click here to Skip to main content
15,074,987 members
Articles / Artificial Intelligence / Machine Learning

Stats

4K views
2 bookmarked

Training a Humanoid AI Robot to Walk Using Proximal Policy Optimisation (PPO)

Rate me:
Please Sign up or sign in to vote.
5.00/5 (3 votes)
29 Sep 2020CPOL4 min read
In this article in the series we start to focus on one particular, more complex environment that PyBullet makes available: Humanoid, in which we must train a human-like agent to walk on two legs.
Here we are using the Proximal Policy Optimisation (PPO) algorithm. We look at: the history of the humanoid environment for reinforcement learning, an introduction to Proximal Policy Optimisation (PPO), and the particular learning parameters that we override.

Views

License

This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Share

About the Author

philoxenic
Web Developer
United Kingdom United Kingdom
No Biography provided

Comments and Discussions