Meta QLearning experiments to optimize robot walking patterns
-
Updated
Aug 24, 2023 - Python
Meta QLearning experiments to optimize robot walking patterns
The code corresponding to the paper "Improving Sample Efficiency of Deep Reinforcement Learning for Bipedal Walking".
In this repository there are the projects developed during the course of Advance Optimization-based Robot Control. The main topics are Task Space Inverse Dynamics (TSID), Differential Dynamic Programming (DDP) and Deep Q-Network (DQN).
Scripts and configuration files to launch when bringing up REEM-C.
A simple random searching technique which provides a competitive approach to Reinforcement learning for Locomotion related tasks on Mu-Jo-Co bodies like Humanoid, Half-Cheetah etc
Implementation of Omnidirectional Walk Using Zero Moment Point (ZMP) and Preview Control Method
Legged Contact Detection (LCD): A deep learning approach for Contact Estimation of Legged Robots using inertial and F/T measurements
Omnidirectional Walking Pattern Generation for Humanoid Robot using ZMP Analytical Method
ROS/ROS2 {BR&SRI} packages for the Humanoid Robots Intelligence Control System Architecture
Add a description, image, and links to the humanoid-walking topic page so that developers can more easily learn about it.
To associate your repository with the humanoid-walking topic, visit your repo's landing page and select "manage topics."