Hierarchical Reinforcement Learning in Matlab

Hi All,

Do anyone has any example that how I can have a Hierarchical Reinforcement Learning in Matlab. I read a paper about Feudal Reinforcement Learning, and I am wondering is there any stright forward step?

Answer 1

[Emmanouil Tzorakoleftherakis]

Hierarchical RL basically comes down to breaking a compelx problem down into smaller 'easier to train' problems, and potentially have multiple loops for high and low-level actions. Here are some examples that illustrate this concept:

https://www.mathworks.com/help/reinforcement-learning/ug/automatic-parking-valet-with-mpc-and-unreal-engine.html

https://www.mathworks.com/help/reinforcement-learning/ug/train-agents-to-control-quanser-qube-pendulum.html

https://www.mathworks.com/help/reinforcement-learning/ug/train-td3-agent-for-pmsm-control.html