Are the functions of offline reinforcement learning integrated into the Reinforcement Learning Toolbox?

Are the functions of offline reinforcement learning integrated into the Reinforcement Learning Toolbox?

Answer 1

[Kautuk Raj]

Since MATLAB R2023a, you can train a reinforcement learning (RL) model offline using existing data through the Reinforcement Learning Toolbox in MATLAB.

This can be done by utilizing the trainFromData function: https://www.mathworks.com/help/reinforcement-learning/ref/rl.agent.rldqnagent.trainfromdata.html

For further details, you can refer to this MATLAB Answers post which addresses a similar query: https://www.mathworks.com/matlabcentral/answers/1707360-offline-training-reinforcement-learning#answer_1515235