Training a Humanoid AI Robot to Walk With Soft Actor Critic (SAC)

philoxenic

Rate me:

5.00/5 (2 votes)

30 Sep 2020CPOL3 min read

6.5K

In this article we will adapt our code to train the Humanoid environment using a different algorithm: Soft Actor-Critic (SAC).

Here we look at: What is SAC, and the meanings of the various learning parameters we have overridden in the code I used for learning the Humanoid environment with SAC.

Views

Daily Counts

This article is part of the series 'Teach a Robot to Walk Deep Reinforcement Learning ◁ Prev View All Next ▷

License

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

Written By

philoxenic

Web Developer

United Kingdom

This member has not yet provided a Biography. Assume it's interesting and varied, and probably something to do with programming.

Comments and Discussions

Teaching a Robot to Walk with AI - Introduction to Continuous Control Environments

Teaching a Robot to Walk with AI and PyBullet Environments

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

Training a Humanoid AI Robot to Walk With Soft Actor Critic (SAC)

Training a Humanoid AI Robot to Run Backwards

Training a Humanoid AI Robot to Run With a Custom Model

Go to top