korymath / ContinuousTimeActorCritic

Continuous Time Natural Actor Critic Reinforcement Learning

ContinuousTimeActorCritic

Continuous Time Natural Actor Critic Reinforcement Learning

This repository is a basic actor-critic reinforcement learning implementation based on the following papers:

and

How can ACRL be used for multi-joint control of robotic limbs?

Continuous Time Natural Actor Critic Reinforcement Learning

Language:Jupyter Notebook 97.8%Language:Python 1.7%Language:Java 0.5%