Error when using Parallel toolbox to train a reinforcement learning agent

Question

Arash MohammadHasani 2022-7-1

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1751630-error-when-using-parallel-toolbox-to-train-a-reinforcement-learning-agent

回答： Gagan Agarwal 2023-12-27

Hi,

I receive the following error when I try to tarin a reinforcement learning agent using parallel computing toolbox

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Gagan Agarwal 2023-12-27

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1751630-error-when-using-parallel-toolbox-to-train-a-reinforcement-learning-agent#answer_1378142

Hi Arash,

I understand that you're encountering difficulties while using parallel processing to train a custom defined RL agent in MATLAB. The issue are encountering is beacuse 'StepsUntilDataIsSent' and 'DataToSendFromWorkers' properties are no longer active for the R2022a version of MATLAB, as indicated in the MATLAB documentation:

https://www.mathworks.com/help/reinforcement-learning/ref/rl.option.rltrainingoptions.html#mw_3ee5a5bb-69a6-46bb-97a0-7428ccfdc5d6

I hope it helps!